© 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. 954
    Prev
    Next
    INDEX
    Explanations

    technical terms and notations related to mathematical equations and graphs

    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
     الرياضيه
    -0.66
     صوتيه
    -0.61
     OFDb
    -0.57
    extAlignment
    -0.56
    OGND
    -0.56
     autorytatywna
    -0.56
     мәкал
    -0.52
    Бахар
    -0.52
    transQ
    -0.52
    ftagPool
    -0.51
    POSITIVE LOGITS
     plotted
    0.81
     plots
    0.77
     plot
    0.75
     comparison
    0.73
     simulated
    0.69
     computed
    0.67
     comparing
    0.65
     Comparison
    0.65
     Plot
    0.65
     Plots
    0.64
    Activations Density 2.549%

    No Known Activations