© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 28434
    Prev
    Next
    INDEX
    Explanations

    specific entities and terms associated with various fields, including culture, biology, and technology

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

    biological and chemical context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fillType
    -0.61
    存于互联网档案馆
    -0.59
    endpush
    -0.57
    webElementXpaths
    -0.55
     @"/
    -0.54
    endphp
    -0.53
    bildēt
    -0.53
    jestic
    -0.53
    ꪼ
    -0.52
    𞤼
    -0.52
    POSITIVE LOGITS
    GraphicsUnit
    0.31
     eventName
    0.30
     poveznice
    0.30
     getCustomer
    0.29
     matériel
    0.27
    sidemargin
    0.27
     resultList
    0.27
     getSystem
    0.27
    最快更新
    0.27
    getKeyCode
    0.26
    Activations Density 0.257%

    No Known Activations