© 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. 0-GEMMASCOPE-RES-16K
    11. 2664
    Prev
    Next
    INDEX
    Explanations

    references to theaters and theatrical concepts

    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
     fundador
    -0.37
     fotógrafo
    -0.36
     delantero
    -0.34
     fondée
    -0.34
     fotografico
    -0.34
     paixão
    -0.34
     černé
    -0.33
     exploración
    -0.33
     imprimible
    -0.33
     mío
    -0.33
    POSITIVE LOGITS
    Reference
    1.00
    References
    0.99
     Reference
    0.94
     References
    0.93
     reference
    0.91
     references
    0.89
    reference
    0.89
    refer
    0.88
     refer
    0.83
    references
    0.82
    Activations Density 0.303%

    No Known Activations