© 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. 8031
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax elements typical in C++ code

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

    C++ standard library namespace declarations and I/O stream operations.

    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
     Guinée
    -0.39
     Tampoco
    -0.28
    ái
    -0.27
    Mark
    -0.25
    Bound
    -0.25
    D
    -0.24
    gevens
    -0.24
     Königreich
    -0.24
    Source
    -0.24
    Peter
    -0.24
    POSITIVE LOGITS
     ویکی‌پدی
    0.87
    httphttps
    0.85
     tartalomajánló
    0.83
    invokeLater
    0.82
     BoxFit
    0.82
     '\\;'
    0.82
    sizeCache
    0.81
    styleType
    0.78
    oredCriteria
    0.77
     للمعارف
    0.77
    Activations Density 0.124%

    No Known Activations