© 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. 3395
    Prev
    Next
    INDEX
    Explanations

    references to programming packages, libraries, files, and data models in code

    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
    出版年
    -0.73
    hyrchwyd
    -0.68
     nakalista
    -0.63
     AssemblyCulture
    -0.60
    ########.
    -0.57
    Datuak
    -0.57
    matchCondition
    -0.51
     Taktlose
    -0.51
     برانيه
    -0.51
     للمعارف
    -0.51
    POSITIVE LOGITS
     controllers
    0.67
     controller
    0.61
     models
    0.59
     domain
    0.57
     IBOutlet
    0.57
     model
    0.56
     views
    0.54
    controller
    0.52
     exceptions
    0.51
    controllers
    0.51
    Activations Density 0.197%

    No Known Activations