© 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. 20-GEMMASCOPE-RES-16K
    11. 430
    Prev
    Next
    INDEX
    Explanations

    function calls and related programming structures

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

    Followed by parentheses

    np_acts-logits-general · gemini-2.0-flash

    code block delimiters

    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
     return
    -1.73
    return
    -1.54
     Return
    -1.45
     returned
    -1.39
     returns
    -1.37
     returning
    -1.35
    Return
    -1.32
     RETURN
    -1.32
     Returns
    -1.19
     Returning
    -1.14
    POSITIVE LOGITS
     EconPapers
    0.81
    Tembelea
    0.81
    AccessorTable
    0.81
    帖最后由
    0.79
    EndProject
    0.75
    saraba
    0.74
     '{@
    0.74
    BeginContext
    0.73
    verwijspagina
    0.71
    AntiForgeryToken
    0.71
    Activations Density 0.068%

    No Known Activations