© 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. 38552
    Prev
    Next
    INDEX
    Explanations

    numerical statistics or events, particularly related to deaths and sports in Georgia

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

    Category:years and events

    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
     loyalty
    -0.39
     Grüsse
    -0.37
     Connectez
    -0.37
     braccia
    -0.35
     support
    -0.35
    intenant
    -0.35
    SqlDataReader
    -0.34
    CloseOperation
    -0.34
     platform
    -0.34
     abbraccio
    -0.34
    POSITIVE LOGITS
    GEBURTSDATUM
    0.64
    Derbyniad
    0.63
    migrationBuilder
    0.62
     autorytatywna
    0.59
    +#+
    0.58
    PreferredItem
    0.55
     Infórmanos
    0.54
    isContained
    0.52
     surla
    0.52
    AnchorStyles
    0.51
    Activations Density 0.035%

    No Known Activations