© 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. 11-GEMMASCOPE-RES-16K
    11. 5367
    Prev
    Next
    INDEX
    Explanations

    references to plotting 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 @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Phosphate
    -0.75
     Hands
    -0.66
    phosphat
    -0.65
    postsleuth
    -0.64
    ſehen
    -0.61
    Hands
    -0.61
     PHOSPH
    -0.61
    parsedMessage
    -0.60
     Paglinawan
    -0.59
    Andi
    -0.59
    POSITIVE LOGITS
     plot
    0.88
     Plot
    0.82
    Plot
    0.79
    plot
    0.73
     Plots
    0.66
     PLOT
    0.66
     plots
    0.65
     Occur
    0.65
    Plots
    0.63
    occur
    0.61
    Activations Density 0.161%

    No Known Activations