© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6057
    Prev
    Next
    INDEX
    Explanations

    elements of code related to object manipulation and control flow in programming

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

    programming-related syntax and programming constructs like method calls, function parameters, and code snippets.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    programming code patterns involving collection iteration and standardized method/callback signatures and parameter lists across languages.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    function parameters in programming code, particularly objects and event arguments.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     HasFactory
    -0.79
    windowFixed
    -0.72
    Personensuche
    -0.72
    tableFuture
    -0.70
     JpaRepository
    -0.68
    ValueStyle
    -0.68
     Chwiliwch
    -0.67
    <unused52>
    -0.67
     zwiſchen
    -0.67
    <unused3>
    -0.66
    POSITIVE LOGITS
    Personendaten
    0.57
    hasNext
    0.36
    MathML
    0.30
    meyi
    0.28
     Haupt
    0.28
     глав
    0.27
     Haupts
    0.27
    define
    0.27
    la
    0.27
     esprits
    0.27
    Activations Density 0.165%

    No Known Activations