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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 72463
    Prev
    Next
    INDEX
    Explanations

    negations or phrases that express denial or rejection

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

    contrasting specific exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    getDoctrine
    -0.38
     houſe
    -0.36
     cliquez
    -0.35
    níka
    -0.34
     ilç
    -0.33
    filé
    -0.32
     handleChange
    -0.31
     padi
    -0.31
    devs
    -0.31
    devServer
    -0.31
    POSITIVE LOGITS
    เฉพาะ
    0.60
     PeEnEo
    0.57
     sauf
    0.57
    IsContent
    0.56
    interopRequire
    0.56
     μόνο
    0.55
    chieht
    0.54
     yalnızca
    0.54
    原始内容存档于
    0.53
     Wicidata
    0.52
    Activations Density 0.020%

    No Known Activations