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. 9297
    Prev
    Next
    INDEX
    Explanations

    themes related to exploitation and manipulation of individuals or groups, particularly in contexts involving race, class, or authority

    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
    tvguidetime
    -0.68
     ExecuteAsync
    -0.62
    UseVisualStyle
    -0.60
    AsUp
    -0.58
    SqlClient
    -0.58
    पया
    -0.55
     JADX
    -0.54
    aarrggbb
    -0.53
    pó
    -0.52
    ↠
    -0.52
    POSITIVE LOGITS
     dumb
    1.82
     stupidity
    1.77
     stupid
    1.77
     Stupid
    1.62
     ignorant
    1.62
    dumb
    1.60
    stupid
    1.60
     idiot
    1.54
     ignorance
    1.53
     foolish
    1.53
    Activations Density 0.358%

    No Known Activations