© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 12387
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface notifications and success messages in programming

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

    UI toast messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ārējās
    -0.36
     StatefulWidget
    -0.35
    Kontrola
    -0.31
    rrggbb
    -0.30
    menuStrip
    -0.28
    ニラ
    -0.28
     vastu
    -0.26
    RequestBody
    -0.26
     مشين
    -0.26
     пау
    -0.24
    POSITIVE LOGITS
     success
    1.02
     flash
    1.01
     alerts
    0.98
    parsedMessage
    0.96
     toast
    0.95
     alert
    0.95
     Success
    0.94
     Toast
    0.94
    flashdata
    0.94
    Success
    0.92
    Activations Density 0.065%

    No Known Activations