© 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. 30-GEMMASCOPE-RES-16K
    11. 10972
    Prev
    Next
    INDEX
    Explanations

    expressions of communication and interaction regarding appointments or responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    A response or reply

    np_acts-logits-general · gemini-2.0-flash

    communication and response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.48
     bezoekers
    -0.43
    イクアウト
    -0.42
     gebouw
    -0.40
     ModelExpression
    -0.39
    richting
    -0.38
    migrationBuilder
    -0.38
     Signalez
    -0.37
    UnsafeEnabled
    -0.37
     pulito
    -0.37
    POSITIVE LOGITS
     reply
    1.95
     responded
    1.87
     respond
    1.87
     response
    1.85
     replies
    1.82
     replying
    1.79
     responses
    1.77
     responds
    1.76
     replied
    1.75
     responding
    1.70
    Activations Density 0.325%

    No Known Activations