© 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. 9642
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to species or contributions in a variety of contexts

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

    Numbers appearing in a quantity

    np_acts-logits-general · gemini-2.0-flash

    quantities and numbers

    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
     deux
    -0.35
     dua
    -0.35
    انجليز
    -0.34
     öne
    -0.33
    labelledby
    -0.32
    سطس
    -0.31
    twice
    -0.31
     }{@
    -0.30
     estekak
    -0.30
     préférences
    -0.30
    POSITIVE LOGITS
     dozens
    1.18
     dozen
    1.16
     hundreds
    0.94
    dozen
    0.90
     numerous
    0.81
     hundred
    0.80
    hundreds
    0.78
     Hundreds
    0.72
     centaines
    0.72
     dizaines
    0.70
    Activations Density 0.394%

    No Known Activations