© 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. 37-GEMMASCOPE-RES-16K
    11. 5185
    Prev
    Next
    INDEX
    Explanations

    references to musical compositions and their composers

    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
     disambiguazione
    -0.71
    MigrationBuilder
    -0.67
    IntoConstraints
    -0.66
    NameInMap
    -0.64
    ftagPool
    -0.61
    Autoritní
    -0.59
    uxxxx
    -0.59
     kaarangay
    -0.57
    addGap
    -0.56
    ----</
    -0.55
    POSITIVE LOGITS
     Variations
    0.56
     Variation
    0.51
     Suite
    0.50
     variations
    0.50
     suite
    0.50
    Variations
    0.48
    scher
    0.48
     movement
    0.48
     variation
    0.47
    Variation
    0.47
    Activations Density 0.159%

    No Known Activations