© 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. 38-GEMMASCOPE-RES-16K
    6. 14460
    Prev
    Next
    INDEX
    Explanations

    keywords related to statistical and analytical processes

    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
    tagHelperRunner
    -1.09
     betweenstory
    -1.00
    ScopeManager
    -0.98
    RegressionTest
    -0.98
     AssemblyCulture
    -0.97
     становника
    -0.95
    ſicht
    -0.93
     للمعارف
    -0.93
    iſche
    -0.93
     resourceCulture
    -0.93
    POSITIVE LOGITS
     specifically
    0.26
     just
    0.25
     not
    0.24
     ALSO
    0.24
    ,
    0.24
     exatamente
    0.23
    where
    0.23
    what
    0.21
     by
    0.21
     perhaps
    0.21
    Activations Density 2.074%

    No Known Activations