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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8418
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax or structure elements such as delimiters and braces

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

    Code snippets

    np_acts-logits-general · gemini-2.0-flash

    code comments and C/C++ syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.63
    []){
    -0.60
    Välislingid
    -0.55
    [])
    -0.52
    Források
    -0.51
    lenir
    -0.49
     geslacht
    -0.48
    "){
    -0.48
    Ể
    -0.48
    Спо
    -0.48
    POSITIVE LOGITS
    DoubleQuotes
    0.72
    LookAnd
    0.69
    AsUp
    0.63
    :✨
    0.62
     الحره
    0.61
    setVerticalGroup
    0.54
    StoryboardSegue
    0.54
    awtextra
    0.54
     Reverso
    0.52
    ArgsConstructor
    0.52
    Activations Density 0.204%

    No Known Activations