© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105573
    Prev
    Next
    INDEX
    Explanations

    terms related to physical systems and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     fruits
    -0.32
     college
    -0.30
     Gag
    -0.30
     ARTICLES
    -0.30
     colleges
    -0.30
     honey
    -0.30
     škoda
    -0.30
     fiat
    -0.29
     former
    -0.29
     fetch
    -0.29
    POSITIVE LOGITS
     snippetHide
    0.73
    ChildScrollView
    0.65
     consultato
    0.62
    oredCriteria
    0.57
    providedIn
    0.54
     समीक्षक
    0.54
    writeFieldEnd
    0.54
    évaluateur
    0.52
     שוליים
    0.52
    Bronnen
    0.52
    Activations Density 0.274%

    No Known Activations