© 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. 116295
    Prev
    Next
    INDEX
    Explanations

    elements related to data structure definitions and queries in a programming context

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

    graphql api and genetics studies

    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
     للاسماء
    -0.70
    Hentet
    -0.64
    AddTagHelper
    -0.64
    MLLoader
    -0.64
    ஢
    -0.63
     مشين
    -0.63
    ஦
    -0.63
    mobileqq
    -0.62
     $_-
    -0.61
    tonsoft
    -0.61
    POSITIVE LOGITS
     gql
    2.03
    apollo
    2.03
    graphql
    0.88
     apollo
    0.70
     graphql
    0.70
     Apollo
    0.57
    Apollo
    0.54
     GraphQL
    0.53
    XmlAccessType
    0.50
    GraphQL
    0.47
    Activations Density 0.001%

    No Known Activations