© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4379
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming libraries and functions

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

    namespace and library identifiers in code (like `java`, `apache`, `std`, `System`).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     AssemblyCulture
    -0.69
    RTGC
    -0.58
    attutto
    -0.56
    Personensuche
    -0.52
     ***!
    -0.52
     invokingState
    -0.50
    mtrl
    -0.50
    нгред
    -0.50
     <=",
    -0.46
    findById
    -0.45
    POSITIVE LOGITS
     FontWeight
    0.56
    KommentareTeilen
    0.49
     colspan
    0.47
    nsyn
    0.42
     initComponents
    0.37
    colgroup
    0.37
     mennesker
    0.36
     uniformes
    0.35
    Couldn
    0.34
     متعلقه
    0.34
    Activations Density 0.548%

    No Known Activations