Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 2989
    Prev
    Next
    INDEX
    Explanations

    occurrences of legal and scientific terminology related to negligence and court procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    უ
    -0.36
    BaseAdapter
    -0.35
     Roque
    -0.35
    renewcommand
    -0.35
     makeStyles
    -0.35
    providedIn
    -0.34
    ToPoint
    -0.34
    ondres
    -0.32
    BibitemOpen
    -0.32
     confounded
    -0.32
    POSITIVE LOGITS
     ur
    1.92
     Ur
    1.83
    ur
    1.75
     UR
    1.75
    UR
    1.71
    Ur
    1.70
     url
    1.66
    url
    1.56
     Url
    1.50
     URL
    1.46
    Activations Density 1.817%

    No Known Activations