© 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
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7971
    Prev
    Next
    INDEX
    Explanations

    JavaScript function definitions and operations related to DOM manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MarshalTo
    -0.46
    writeFieldEnd
    -0.46
    EDEFAULT
    -0.41
     '{@
    -0.35
     punishable
    -0.35
    CodeAttribute
    -0.34
    Иск
    -0.34
    хьтан
    -0.34
     Lak
    -0.33
    Trama
    -0.33
    POSITIVE LOGITS
     document
    1.24
    document
    1.19
    addEventListener
    0.79
     Document
    0.76
    Document
    0.74
    getElementById
    0.73
     documents
    0.72
     dokument
    0.72
    querySelector
    0.71
     getElement
    0.71
    Activations Density 0.266%

    No Known Activations