© 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. 20-GEMMASCOPE-RES-16K
    11. 6406
    Prev
    Next
    INDEX
    Explanations

    statistical properties and performance metrics in numerical data analysis

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

    technical or scientific language describing statistical measurements, energy, or performance characteristics.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    comparative statements about characteristics being greater, higher, shorter, or more/less intense than others.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.60
    InjectAttribute
    -0.59
    GEBURTSDATUM
    -0.57
     Biôgrafia
    -0.56
    ьаж
    -0.56
    RTLU
    -0.54
    abestanden
    -0.50
    ніципа
    -0.49
    sodik
    -0.49
    uisine
    -0.49
    POSITIVE LOGITS
     fewer
    0.54
     Fewer
    0.54
     harder
    0.47
     deeper
    0.42
     daripada
    0.41
     more
    0.39
     dibanding
    0.39
     steeper
    0.38
     less
    0.38
     overall
    0.37
    Activations Density 0.571%

    No Known Activations