Instructions to use google/gemma-scope-2b-pt-res with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- SAELens
How to use google/gemma-scope-2b-pt-res with SAELens:
# pip install sae-lens from sae_lens import SAE sae, cfg_dict, sparsity = SAE.from_pretrained( release = "RELEASE_ID", # e.g., "gpt2-small-res-jb". See other options in https://github.com/jbloomAus/SAELens/blob/main/sae_lens/pretrained_saes.yaml sae_id = "SAE_ID", # e.g., "blocks.8.hook_resid_pre". Won't always be a hook point ) - Notebooks
- Google Colab
- Kaggle
Download layer_19/width_65k/average_l0_21/params.npz from google/gemma-scope-2b-pt-res: direct link, hf CLI and curl.
- Browser
- Download file 1.21 GB
-
https://huggingface.co/google/gemma-scope-2b-pt-res/resolve/main/layer_19/width_65k/average_l0_21/params.npz
- Command line
-
hf download hf://google/gemma-scope-2b-pt-res/layer_19/width_65k/average_l0_21/params.npz
-
curl -L -o params.npz https://huggingface.co/google/gemma-scope-2b-pt-res/resolve/main/layer_19/width_65k/average_l0_21/params.npz
1.21 GB
- Xet hash:
- b0eab58a1f5e787c3b7ed8d0ef8f782f6c886b427c67c90c5675449174e73374
- Size of remote file:
- 1.21 GB
- SHA256:
- 660f67fac6ae4e6162c1df5158495334c2ae47148c302b0bf4c8a2fec5d27f07
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.