© 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. 0-GEMMASCOPE-RES-16K
    11. 10046
    Prev
    Next
    INDEX
    Explanations

    technical terminology and structured data in code and legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ことなく
    -0.35
     tatlı
    -0.32
    ͛
    -0.32
    Lotto
    -0.31
    ไว้
    -0.31
     Gleichzeitig
    -0.31
     آخرین
    -0.29
    simult
    -0.29
     Zukunft
    -0.29
    意的
    -0.29
    POSITIVE LOGITS
     estekak
    0.74
     AssemblyCulture
    0.68
     kasarigan
    0.68
    ThroughAttribute
    0.68
    PostInfinity
    0.67
    GOTREF
    0.65
    IntoConstraints
    0.65
    TypedDataSet
    0.65
    SourceChecksum
    0.64
    +#+
    0.63
    Activations Density 1.414%

    No Known Activations