© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2489
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs and syntax

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

    closing parentheses and semicolons that terminate function declarations and method signatures in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     muß
    -0.45
    rosio
    -0.36
    wußt
    -0.36
     idéia
    -0.36
    CONSIN
    -0.36
    faßt
    -0.36
    iPhone
    -0.35
     daß
    -0.35
    
    -0.35
     جغرافيا
    -0.34
    POSITIVE LOGITS
    auto
    0.73
     auto
    0.71
     constexpr
    0.62
     GoogleFonts
    0.55
     HasFactory
    0.55
    ArrowToggle
    0.52
    >{@
    0.52
    emplace
    0.52
     covid
    0.50
    :✨
    0.50
    Activations Density 0.546%

    No Known Activations