© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 880
    Prev
    Next
    INDEX
    Explanations

    references to terms with multiple interpretations or meanings in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputBorder
    -0.47
    іод
    -0.41
     ModelExpression
    -0.40
    Autoritní
    -0.38
    riction
    -0.38
    recated
    -0.37
     الاطلاع
    -0.36
    lielmo
    -0.35
    вік
    -0.34
    SharedCtor
    -0.33
    POSITIVE LOGITS
     meaning
    2.70
     meanings
    2.27
    meaning
    2.23
     Meaning
    2.22
    Meaning
    2.16
     significado
    1.97
     significance
    1.78
     significato
    1.77
     significados
    1.69
     betekenis
    1.60
    Activations Density 0.740%

    No Known Activations