© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 11774
    Prev
    Next
    INDEX
    Explanations

    stuctural elements and attributes in code or markup language

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

    Code-related characters/punctuation

    np_acts-logits-general · gemini-2.0-flash

    end; or end)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteAttribute
    -0.70
    SOUNDBITE
    -0.63
     roxo
    -0.60
    getConnection
    -0.59
     Torrey
    -0.58
     ilustra
    -0.57
    RenderAtEndOf
    -0.57
     Hano
    -0.56
    prove
    -0.56
     proves
    -0.56
    POSITIVE LOGITS
     cherchés
    0.54
    jsoup
    0.53
     {
    0.53
    {
    0.49
     cela
    0.49
    •
    0.48
    :
    0.48
    ">
    0.48
    >
    0.47
    Permalink
    0.46
    Activations Density 0.046%

    No Known Activations