© 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. 20-GEMMASCOPE-RES-131K
    11. 106922
    Prev
    Next
    INDEX
    Explanations

    syntactical elements and structure in programming code

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

    closing brackets and 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
     Infórmanos
    -0.85
    ReusableCell
    -0.82
     verſch
    -0.80
     zwiſchen
    -0.78
    ſſung
    -0.77
     ſehen
    -0.77
    tagHelperRunner
    -0.76
    tagext
    -0.76
    ſicht
    -0.76
    niſſe
    -0.75
    POSITIVE LOGITS
    .
    0.29
     imprimée
    0.27
    ceedings
    0.27
    ..
    0.26
    then
    0.26
     بع
    0.26
     auxquelles
    0.24
    attached
    0.24
     polí
    0.24
    AnimationsModule
    0.23
    Activations Density 0.038%

    No Known Activations