Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9540
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and phrases indicating ownership or favorites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    คม
    -0.44
    unca
    -0.41
    LookAnd
    -0.41
    átu
    -0.40
     getInstance
    -0.39
     Blair
    -0.38
    зован
    -0.38
     subpo
    -0.38
    NOS
    -0.37
     should
    -0.37
    POSITIVE LOGITS
     favorite
    3.04
     favourite
    2.78
    favorite
    2.63
     favorites
    2.57
     Favorite
    2.47
    favourite
    2.37
     FAVORITE
    2.33
     favourites
    2.33
    Favorite
    2.32
     Favourite
    2.25
    Activations Density 0.143%

    No Known Activations