© 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. 7274
    Prev
    Next
    INDEX
    Explanations

    code snippets and component structures in JavaScript or React

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

    code syntax and technical markup patterns like JSX tags, arrow functions, and curly braces.

    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
    CodeAttribute
    -0.63
    delwed
    -0.61
    <?
    -0.56
    postsleuth
    -0.54
    OGND
    -0.54
    #+#
    -0.54
    /**
    -0.52
     utafitiHapana
    -0.52
     AssemblyVersion
    -0.51
    nofollow
    -0.51
    POSITIVE LOGITS
     React
    0.90
     react
    0.77
    React
    0.73
     props
    0.70
    react
    0.69
     component
    0.67
     Component
    0.62
    componentDid
    0.61
    props
    0.59
     REACT
    0.59
    Activations Density 0.211%

    No Known Activations