© 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. 38-GEMMASCOPE-RES-16K
    11. 7217
    Prev
    Next
    INDEX
    Explanations

    statements referring to personal identities and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.56
     Containing
    -0.47
    ⓧ
    -0.46
    $_['
    -0.46
     которое
    -0.44
    colhead
    -0.43
     initComponents
    -0.43
     amelyek
    -0.42
    ukone
    -0.42
    SuspendLayout
    -0.42
    POSITIVE LOGITS
     married
    0.82
     obsessed
    0.75
     fluent
    0.75
     part
    0.72
     addicted
    0.72
     involved
    0.69
     passionate
    0.68
     employed
    0.67
    married
    0.67
     affiliated
    0.66
    Activations Density 0.536%

    No Known Activations