© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11660
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or words beginning with "Wil."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens starting with "Wil" followed by a letter

    np_acts-logits-general · gemini-2.0-flash

    Wil- prefix names

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ContentAlignment
    -0.69
     InputDecoration
    -0.65
     désolés
    -0.65
    enumi
    -0.57
    \{\\
    -0.56
    سوب
    -0.56
    jspx
    -0.55
     faptul
    -0.55
     Brot
    -0.54
     numberWith
    -0.53
    POSITIVE LOGITS
    fully
    0.70
    RenderAtEndOf
    0.61
    power
    0.61
    Power
    0.58
    fulness
    0.56
    oughby
    0.55
     Power
    0.54
     power
    0.54
    POWER
    0.53
     dieux
    0.53
    Activations Density 0.061%

    No Known Activations