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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 85664
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the definite article "the" in various contexts

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

    the value, list, item, request, resource, view, user

    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
     GenerationType
    -0.45
    ByVersion
    -0.38
    isContained
    -0.38
    PerformLayout
    -0.37
    RenderAtEndOf
    -0.36
     FontFamily
    -0.35
    SharedDtor
    -0.35
     Administrativna
    -0.35
    pageIndex
    -0.34
     versi
    -0.34
    POSITIVE LOGITS
     tả
    0.57
    RectangleBorder
    0.57
     zijne
    0.55
    thmetic
    0.55
    bulin
    0.53
     the
    0.53
     ואת
    0.52
    หว่าง
    0.48
     Exacts
    0.48
    arangay
    0.48
    Activations Density 0.003%

    No Known Activations