© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 6547
    Prev
    Next
    INDEX
    Explanations

    mentions of official or authorized products and services

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

    official affiliation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    htaccess
    -0.35
    Portály
    -0.35
    тьи
    -0.35
    rspec
    -0.34
    相談
    -0.33
    wnicy
    -0.33
    imageshack
    -0.32
    sihkan
    -0.31
    seende
    -0.31
    orderid
    -0.30
    POSITIVE LOGITS
     official
    3.02
    official
    2.73
    Official
    2.63
     Official
    2.59
     OFFICIAL
    2.47
     officially
    2.44
     oficial
    2.39
    OFFICIAL
    2.38
     offizielle
    2.31
     oficjal
    2.25
    Activations Density 0.085%

    No Known Activations