© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 4391
    Prev
    Next
    INDEX
    Explanations

    references to notable or "great" events, concepts, or characters

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

    the word "great" followed by a noun

    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
    ThroughAttribute
    -0.45
    ibatkan
    -0.45
    ColumnHeaders
    -0.44
     '{@
    -0.39
    Хьажоргаш
    -0.39
    
    -0.37
     miniaturka
    -0.37
    kozás
    -0.37
    DockStyle
    -0.37
    躇
    -0.36
    POSITIVE LOGITS
    CompanyId
    0.48
     Grid
    0.46
     Agent
    0.46
    godic
    0.46
     Therm
    0.46
    AuthGuard
    0.45
     Surveys
    0.44
    geving
    0.44
     Crunch
    0.43
    providedIn
    0.43
    Activations Density 0.185%

    No Known Activations