© 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. 20-GEMMASCOPE-RES-131K
    11. 106614
    Prev
    Next
    INDEX
    Explanations

    the names of individuals and their speech attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Normdatei
    -0.72
     Италијани
    -0.71
    uxxxx
    -0.70
    astéroïdes
    -0.68
    IsContent
    -0.66
    Vidite
    -0.66
     nonUne
    -0.66
    ChildScrollView
    -0.66
     مرئيه
    -0.66
    tvguidetime
    -0.65
    POSITIVE LOGITS
    .
    0.37
    verifyException
    0.32
    ViewImports
    0.30
     termica
    0.30
    console
    0.30
     Augen
    0.29
    <h1>
    0.29
     pouvoirs
    0.29
     vaiz
    0.29
    it
    0.28
    Activations Density 0.006%

    No Known Activations