© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 30-GEMMASCOPE-RES-16K
    11. 10136
    Prev
    Next
    INDEX
    Explanations

    sequences of excluded items and their statistical impact in analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or statistical analysis/calculations

    np_acts-logits-general · gemini-2.0-flash

    statistical analyses and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     complete
    -0.32
    ^_^
    -0.31
    complete
    -0.31
     confirmed
    -0.30
     ?>">
    -0.30
     recently
    -0.29
     posiad
    -0.29
    bel
    -0.28
    booth
    -0.28
    Se
    -0.27
    POSITIVE LOGITS
     calculations
    1.05
     computations
    0.96
    AndEndTag
    0.90
     calculation
    0.85
    verifyException
    0.81
     ब्रेकडाउन
    0.80
     computation
    0.79
    calculations
    0.78
     analyses
    0.78
     comparisons
    0.77
    Activations Density 1.738%

    No Known Activations