© 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. 2231
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and structure in programming languages

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

    programming code syntax, specifically data types and class property definitions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    ILLO
    -0.35
     proxy
    -0.35
    fois
    -0.35
     físicos
    -0.35
    moine
    -0.34
     FT
    -0.32
    zke
    -0.32
    readFileSync
    -0.32
     coque
    -0.32
     cảnh
    -0.32
    POSITIVE LOGITS
    AnchorTagHelper
    0.66
     informée
    0.62
    RTEE
    0.59
    Personendaten
    0.59
     ModelExpression
    0.58
    ArrowToggle
    0.58
     ExecuteAsync
    0.57
    IUrlHelper
    0.53
    rawDesc
    0.52
     ویکی‌پدی
    0.52
    Activations Density 0.408%

    No Known Activations