© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 106736
    Prev
    Next
    INDEX
    Explanations

    terms related to web service connections and subscriptions

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

    publish, Test, glucose, activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.73
    RectangleBorder
    -0.72
    AsUp
    -0.71
     betweenstory
    -0.67
    styleType
    -0.62
    WithIOException
    -0.60
     ويكيپيديا
    -0.60
    argout
    -0.59
    खरीदारी
    -0.59
    aarrggbb
    -0.59
    POSITIVE LOGITS
    гли
    0.34
     Fant
    0.27
    websocket
    0.27
    ё
    0.26
    WebSocket
    0.26
     Doc
    0.26
     compositeur
    0.26
     chip
    0.25
     toit
    0.25
    siąż
    0.24
    Activations Density 0.016%

    No Known Activations