© 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. 38-GEMMASCOPE-RES-16K
    11. 10234
    Prev
    Next
    INDEX
    Explanations

    technical vocabulary related to programming plots and data visualization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kick
    -0.34
     resourceCulture
    -0.33
    bitField
    -0.33
    Kick
    -0.32
    interview
    -0.32
    sizeCache
    -0.32
    Interview
    -0.31
     Kick
    -0.31
     سر
    -0.31
    pointer
    -0.30
    POSITIVE LOGITS
     plot
    1.99
     plots
    1.97
     Plot
    1.77
     Plots
    1.73
    plot
    1.69
     plotting
    1.63
    Plot
    1.62
     PLOT
    1.59
    plots
    1.57
    Plots
    1.56
    Activations Density 0.940%

    No Known Activations