© 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 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. 15273
    Prev
    Next
    INDEX
    Explanations

    closing braces and other structural elements in code

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

    closing braces and end-of-block syntax in code.

    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
    AnchorTagHelper
    -0.64
     nahilalakip
    -0.61
     lenker
    -0.57
    XmlAccessType
    -0.52
     برانيه
    -0.48
    astéro
    -0.48
     rhestr
    -0.46
    __);
    -0.45
    acus
    -0.44
    ngdoc
    -0.44
    POSITIVE LOGITS
    rrggbb
    0.47
     &___
    0.43
     unknownFields
    0.40
    paravant
    0.40
     titolata
    0.39
     identité
    0.38
     abſ
    0.37
     voort
    0.37
     tratti
    0.36
    ViewImports
    0.36
    Activations Density 0.084%

    No Known Activations