© 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. 21-GEMMASCOPE-RES-16K
    11. 10816
    Prev
    Next
    INDEX
    Explanations

    terms related to cellular and molecular processes in medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StateException
    -0.37
     initComponents
    -0.36
    KommentareTeilen
    -0.35
    bootstrapcdn
    -0.35
    Whose
    -0.29
     mobili
    -0.28
    WillAppear
    -0.28
     mobilisation
    -0.28
     dramat
    -0.28
    rspec
    -0.28
    POSITIVE LOGITS
    AnchorStyles
    0.77
    MigrationBuilder
    0.66
    extAlignment
    0.63
    ValueStyle
    0.61
     zupeł
    0.57
    ConstraintMaker
    0.57
     AssemblyCulture
    0.56
    RectangleBorder
    0.56
    archiviato
    0.54
     RequestMethod
    0.54
    Activations Density 1.188%

    No Known Activations