© 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. 28-GEMMASCOPE-RES-16K
    11. 3790
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to code and programming functionalities

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

    Follows a period, parenthesis, or bracket

    np_acts-logits-general · gemini-2.0-flash

    Martinez at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diet
    -0.40
    requestBody
    -0.37
     li
    -0.36
    GetRequest
    -0.36
    RequestBody
    -0.35
    HttpMethod
    -0.34
    addButton
    -0.34
     Dun
    -0.34
    IsEnabled
    -0.34
    MeasureSpec
    -0.34
    POSITIVE LOGITS
     success
    0.80
    parsedMessage
    0.79
     result
    0.78
     결과
    0.74
     successes
    0.73
     results
    0.72
     Success
    0.72
     response
    0.72
    SourceChecksum
    0.70
     risultato
    0.70
    Activations Density 0.692%

    No Known Activations