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

    Neuronpedia

    Jacobian LensNEW
    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. 35900
    Prev
    Next
    INDEX
    Explanations

    code-related elements, specifically function definitions and variable declarations

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

    code block starters and variable declarations

    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
     iNdEx
    -0.37
    astify
    -0.34
    (!__
    -0.32
    FromNib
    -0.30
    DoubleQuotes
    -0.29
     ung
    -0.29
    OrNil
    -0.29
     Loeb
    -0.28
     OFDb
    -0.28
     drums
    -0.28
    POSITIVE LOGITS
     autorytatywna
    0.69
    migrationBuilder
    0.65
    LLocation
    0.59
    Portail
    0.58
    RTLU
    0.56
    parsedMessage
    0.56
     CURIAM
    0.55
    PathVariable
    0.54
     endwhile
    0.52
     Beaches
    0.52
    Activations Density 0.105%

    No Known Activations