Model details
模型介绍 中文整理 Model use case Gemma Scope 2 是一个全面开源的稀疏自编码器和转码器套件,专为 Gemma 3 模型系列设计。该套件可帮助分析模型的内部激活,将其分解为底层概念,类似于生物学家使用显微镜研究动植物的单个细胞。
主要能力
提供针对 Gemma 3 多种参数规模(270M、1B、4B、12B、27B)的预训练和指令微调模型的稀疏自编码器。包含多层 SAE 变体:部分残差流交叉编码器和跨层转码器。
运行要求 本仓库包含在 Gemma V3 4B IT 上训练的稀疏自编码器和转码器。模型宽度支持 16k、64k、256k、1m 四种规格。L0 目标值分为 small(10-20)、medium(30-60)、large(60-150)三档。
基本用法 单层模型:resid post、attn out、mlp out 分别在模型的残差流、注意力输出、MLP 输出的 4 个不同层级(25%、50%、65%、85% 深度)训练 SAE。transcoder 包含在同一 4 层上训练的转码器。resid post all、attn out all、mlp out all、transcoder all 覆盖模型的每个层级。
多层模型:crosscoder 在残差流的 4 个连续层级上训练弱因果交叉编码器。clt 跨层转码器从每个 MLP 层之前的残差流值重建整个模型的 MLP 输出。
选择建议:除完整电路分析外,推荐使用层级子文件夹中的 SAE 或转码器。宽度推荐 64k 或 256k。L0 推荐 "medium",适用于大多数任务。
限制 具体功能特性和性能表现需参考 Neuronpedia 页面获取定性了解。不同宽度和 L0 值会影响可提取的特征类型,需根据具体用例选择。
License CC-BY-4.0(知识共享署名 4.0 国际许可证)
优先采用原作者提供的中文模型卡片;仅有英文说明时由闲社AI翻译整理。重要参数、许可证和商用范围请以原文为准。
你将获得什么 完整仓库方式包含该固定版本中的权重、配置、分词器及说明文件;指定版本方式只下载所选文件或整组分片。多模态模型的投影文件、配置等依赖,请按作者说明配齐。
完整仓库可能包含多个权重格式,因此需要的磁盘空间可能大于单一格式的模型大小。下载文件不等于完成模型部署。
使用前须知 运行环境 运行模型需要的设备、工具与依赖,以原作者说明为准。
授权范围 是否允许商用、修改和分发,请查看模型许可证。
闲社提供资料与镜像下载方法,不代表已运行模型或完成安全审计。下载的代码应先检查,再执行。
Problem with the information or download? Sign in to submit feedback.
Pinned version · Multiple download options
gemma-scope-2-4b-it model download Download the full repository or choose a version or file.
Choose a download source China mirror (recommended) Hugging Face official
已根据访问地区推荐 Hugging Face 官方线路,你可以手动切换。
Choose what to download
Full repository · All files Selected version / file
Need just one GGUF precision? Load the file manifest and choose a version. Direct file links do not require Python; the command below can download multiple shards together.
Load available versions and files
Quantization / file Load the manifest to choose
This reads the pinned version's file manifest; no model weights are downloaded.
Choose your operating system Windows · PowerShell Linux / macOS · Terminal
For command-line downloads, follow these steps to get the full repository or selected files. Direct file links do not need these steps.
1 Open a terminal window Create and open a folder for the model. In the folder's address bar, enter powershell and press Enter.
If Python is not installed, get it from the official Python website . In the terminal, enter python --version; continue when a version number appears.
2 First time? Install the download tool Copy this command, paste it into the terminal, press Enter and wait for installation to finish.
python -m pip install --upgrade huggingface_hubCopy install command Already installed? Continue to step 3.
3 Run the download command Select the button below, paste into the same terminal and press Enter. The tool downloads all files included in the current command.
Copy full download command
Copying does not start a download. Paste and run the command on your device.
Where are the downloaded files? Open the folder you chose. Look for the models folder. When progress stops and the terminal returns to its prompt without errors, check that all files are present. 'Copied' does not mean 'downloaded'.
No response or an error? python not found: Install Python and reopen the terminal. On Windows, follow the installer's instructions to enable command-line access.
hf not found: Confirm that step 2 succeeded, then reopen the terminal. If needed, add Python's Scripts folder to your user PATH. Do not repeatedly download scripts.
Network interrupted: Stay in the same folder and run the same command again. The tool checks existing files.
Permission or disk error: Choose a writable folder with enough free space. Do not disable system security protection.
View the full download command
请开启浏览器脚本,或使用默认 Windows 教程并展开命令手动复制执行。