Instructions to use google/gemma-scope-2b-pt-transcoders with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- SAELens
How to use google/gemma-scope-2b-pt-transcoders 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_3/width_16k/average_l0_167/params.npz from google/gemma-scope-2b-pt-transcoders: direct link, hf CLI and curl.
- Browser
- Download file 302 MB
-
https://huggingface.co/google/gemma-scope-2b-pt-transcoders/resolve/main/layer_3/width_16k/average_l0_167/params.npz
- Command line
-
hf download hf://google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_167/params.npz
-
curl -L -o params.npz https://huggingface.co/google/gemma-scope-2b-pt-transcoders/resolve/main/layer_3/width_16k/average_l0_167/params.npz
302 MB
- Xet hash:
- 50a3f3f99d9960553d48cf810cfaaeb5428fccbe1391e8305315be0921c8d42a
- Size of remote file:
- 302 MB
- SHA256:
- b2c96c1fb2d2b8585c1579eafd08f56550fb1273beec69f5ee8b400d3e88d259
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.