Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2644
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and database operations

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

    INSERT INTO statements, golf courses, lists

    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
     ब्रेकडाउन
    -0.71
    Personensuche
    -0.68
     المعيارى
    -0.68
     defaultstate
    -0.67
    sizeCache
    -0.64
    
    -0.61
    contentLoaded
    -0.60
    NameInMap
    -0.57
     Administrativna
    -0.57
    DoubleQuotes
    -0.57
    POSITIVE LOGITS
    basicConfig
    0.38
    Hintergrund
    0.31
    auto
    0.29
     Moyen
    0.28
     sauve
    0.28
    ivotopis
    0.28
    setViewportView
    0.28
    bangun
    0.28
    uchsia
    0.28
    ième
    0.28
    Activations Density 0.316%

    No Known Activations