© 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
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 15277
    Prev
    Next
    INDEX
    Explanations

    references to specific publications, authors, or components related to scientific or medical research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     câte
    -0.45
     gewöhnlich
    -0.39
     oč
    -0.37
     Namens
    -0.36
     Trabajo
    -0.36
     jiwa
    -0.36
     TRABAJO
    -0.35
     cubiertos
    -0.35
     Puedes
    -0.34
     ajustable
    -0.34
    POSITIVE LOGITS
     ModelExpression
    1.07
    UrlResolution
    0.96
    Hochspringen
    0.86
    WireFormatLite
    0.85
    GraphicsUnit
    0.84
    expandindo
    0.83
     Infórmanos
    0.82
     MainAxisSize
    0.80
    LookAnd
    0.79
     betweenstory
    0.78
    Activations Density 0.716%

    No Known Activations