© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12006
    Prev
    Next
    INDEX
    Explanations

    programming syntax and code structure components

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

    Code-related terms and programming syntax

    np_acts-logits-general · gemini-2.0-flash

    code structure and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    Datuak
    -0.84
     препратки
    -0.77
    ValueStyle
    -0.76
     JpaRepository
    -0.75
    tableFuture
    -0.75
     HasFactory
    -0.73
    httphttps
    -0.72
    Personensuche
    -0.70
     BoxFit
    -0.70
    SPATH
    -0.70
    POSITIVE LOGITS
    Personendaten
    0.54
     dependencia
    0.30
     Haupt
    0.29
    hasNext
    0.28
     глав
    0.28
    MathML
    0.28
    log
    0.28
     femenina
    0.28
     hal
    0.27
    ftet
    0.27
    Activations Density 0.229%

    No Known Activations