© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 17341
    Prev
    Next
    INDEX
    Explanations

    elements and variables related to mathematical expressions, especially in the context of equations and their components

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

    mathematical expressions and code

    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
    aarrggbb
    -0.82
     للاسماء
    -0.80
     незавершена
    -0.76
     ویکی‌پدی
    -0.71
    Panamoan
    -0.67
     ProtoMessage
    -0.67
     ब्रेकडाउन
    -0.66
    SharedDtor
    -0.61
    AsUp
    -0.61
    InputTagHelper
    -0.60
    POSITIVE LOGITS
     aç
    0.40
     CallOverrides
    0.37
    voix
    0.35
    redd
    0.34
    kungen
    0.34
     xoay
    0.34
    syl
    0.33
    CDCl
    0.33
     onBind
    0.32
    uckle
    0.32
    Activations Density 0.551%

    No Known Activations