© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5860
    Prev
    Next
    INDEX
    Explanations

    references to statistical data and measurements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    numerical values, particularly decimal numbers, percentages, and measurements in scientific or medical texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ordinaires
    -0.46
     Vors
    -0.43
    Muerte
    -0.42
     pério
    -0.40
     vectorielle
    -0.40
     académica
    -0.39
     exécu
    -0.39
     faveur
    -0.39
     chaude
    -0.37
     saurait
    -0.37
    POSITIVE LOGITS
     незавершена
    0.75
    pushFollow
    0.70
     Signalez
    0.69
    Хьажоргаш
    0.69
    featureID
    0.68
     payed
    0.68
     المعيارى
    0.67
    principalTable
    0.66
     Chwiliwch
    0.65
     peculiarities
    0.63
    Activations Density 5.045%

    No Known Activations