© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5896
    Prev
    Next
    INDEX
    Explanations

    references to legal terms or aspects of a court case

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

    whitespace and formatting characters (tabs, spaces, line breaks) that separate sections or structure documents.

    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
    QMetaType
    -0.73
    parsedMessage
    -0.71
    featureID
    -0.67
    verwijspagina
    -0.66
     AssemblyCulture
    -0.66
    enablog
    -0.63
     BorderSide
    -0.62
     ujednoznacz
    -0.61
     ddelwed
    -0.60
    Spolja
    -0.60
    POSITIVE LOGITS
    <blockquote>
    1.23
    <h2>
    1.04
    <h4>
    0.92
    <h3>
    0.91
    0.87
    <h1>
    0.83
    ↵↵
    0.77
    *
    0.77
    <tr>
    0.75
    \[
    0.74
    Activations Density 1.105%

    No Known Activations