© 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 EvalsExportsinterp-engineNEWAPI 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. 29483
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords, particularly variable and constant declarations

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

    javascript, c++, and objective-c keywords

    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
    AnimationsModule
    -0.58
    tagHelperRunner
    -0.57
    principalColumn
    -0.56
     nahilalakip
    -0.56
    ChildScrollView
    -0.54
    httphttps
    -0.54
    bootstrapcdn
    -0.54
    ScopeManager
    -0.53
     estekak
    -0.53
    URLException
    -0.52
    POSITIVE LOGITS
    ########.
    0.43
    var
    0.42
     scaling
    0.40
    const
    0.40
     skall
    0.40
    のだが
    0.39
     baked
    0.38
    ських
    0.38
     const
    0.38
     re
    0.37
    Activations Density 0.129%

    No Known Activations