© 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. 20-GEMMASCOPE-RES-131K
    11. 78767
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation in the context of coding or markup language syntax

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

    code delimiters and structure

    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
    migrationBuilder
    -0.73
    enablog
    -0.72
    niſſe
    -0.68
    ſchaft
    -0.67
    iſen
    -0.66
     imagui
    -0.65
    linawan
    -0.65
    ementara
    -0.65
    ðsíða
    -0.65
     deſſen
    -0.63
    POSITIVE LOGITS
     simplifié
    0.37
    دانشنامهٔ
    0.36
    intervento
    0.33
    TagMode
    0.28
    dicionado
    0.26
    AnchorStyles
    0.26
    style
    0.25
     suela
    0.25
     CascadeType
    0.24
     mitään
    0.24
    Activations Density 0.038%

    No Known Activations