© 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
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 1282
    Prev
    Next
    INDEX
    Explanations

    references to primary and secondary categories or types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grüsse
    -0.77
     sostenibilidad
    -0.72
     financiación
    -0.68
    parsedMessage
    -0.66
     garantías
    -0.65
     bluza
    -0.63
     legado
    -0.63
     fédé
    -0.62
     locura
    -0.62
     bluzka
    -0.62
    POSITIVE LOGITS
     secondary
    0.92
     Na
    0.85
     Primary
    0.82
     primary
    0.82
     Secondary
    0.78
    Primary
    0.76
     Empty
    0.75
    Empty
    0.73
    primary
    0.68
    secondary
    0.68
    Activations Density 0.318%

    No Known Activations