© 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. 15518
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and syntax relevant to code structure and function definitions

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

    function or method calls with parentheses containing parameters.

    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
    PreferredItem
    -0.52
    esez
    -0.47
     strdup
    -0.46
    toMatchSnapshot
    -0.46
    EDEFAULT
    -0.46
    irvana
    -0.45
    Datuak
    -0.44
     wikipagina
    -0.44
    hadur
    -0.43
    cerpt
    -0.43
    POSITIVE LOGITS
    (&
    1.05
     &
    1.02
    &
    0.83
    ,&
    0.80
     (&
    0.79
    ",&
    0.75
    =&
    0.74
    :&
    0.73
     \&
    0.73
    *)&
    0.65
    Activations Density 0.224%

    No Known Activations