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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 58450
    Prev
    Next
    INDEX
    Explanations

    references to legal policies and compliance regulations

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

    section numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.75
     Administrativna
    -0.68
    хьтан
    -0.56
     שוליים
    -0.55
    QtWidgets
    -0.55
    EndContext
    -0.55
    الدراسه
    -0.54
    migrationBuilder
    -0.54
    DeleteBehavior
    -0.54
    ScopeManager
    -0.52
    POSITIVE LOGITS
     le
    0.30
    ThemeOverlay
    0.29
     obra
    0.28
     Talbot
    0.27
    空白
    0.26
     друга
    0.26
     local
    0.26
     NSCoder
    0.26
     legislative
    0.26
     pouvoirs
    0.26
    Activations Density 0.324%

    No Known Activations