© 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. 31-GEMMASCOPE-RES-131K
    11. 61323
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and structure-related tokens in code snippets

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

    closing parentheses, semicolons, or brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    piecze
    -0.32
    ########.
    -0.28
     calendriers
    -0.26
    テンツ
    -0.24
    GtkWidget
    -0.23
    Pyx
    -0.22
    舺
    -0.21
    േ
    -0.20
    细
    -0.20
    -------------</
    -0.20
    POSITIVE LOGITS
    Jîn
    0.82
    majánló
    0.78
    IUrlHelper
    0.74
     propOrder
    0.72
    ValueGeneration
    0.71
    CloseOperation
    0.68
    principalColumn
    0.67
     BoxFit
    0.67
    prepareStatement
    0.67
     MessageBoxIcon
    0.66
    Activations Density 0.049%

    No Known Activations