© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 3898
    Prev
    Next
    INDEX
    Explanations

    relationships and comparisons between results in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.52
    dicionado
    -0.33
    RemoveField
    -0.32
    󠁴
    -0.31
    ẵng
    -0.31
     linkovi
    -0.30
    dolu
    -0.30
     nargin
    -0.30
    ónicos
    -0.29
    IsMutable
    -0.29
    POSITIVE LOGITS
     results
    3.84
     Results
    3.25
    results
    3.22
     result
    3.20
    Results
    3.11
     resultados
    3.06
     résultats
    3.02
     resultado
    2.95
     RESULTS
    2.95
    结果
    2.92
    Activations Density 3.650%

    No Known Activations