© 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. 38-GEMMASCOPE-RES-16K
    11. 13372
    Prev
    Next
    INDEX
    Explanations

    keywords related to code structure and programming operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.37
    お世話
    -0.35
     Comprometido
    -0.35
     nullptr
    -0.34
     this
    -0.33
    ligheter
    -0.33
     adentro
    -0.33
    Tembelea
    -0.32
     aquela
    -0.31
     Stellung
    -0.31
    POSITIVE LOGITS
    guard
    0.87
     guard
    0.77
     Guard
    0.69
    QMetaType
    0.69
     GUARD
    0.69
     للاسماء
    0.66
    Guard
    0.59
     Dispatch
    0.58
    self
    0.56
    autoreleasepool
    0.56
    Activations Density 0.334%

    No Known Activations