© 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. 40-GEMMASCOPE-RES-16K
    11. 8546
    Prev
    Next
    INDEX
    Explanations

    references to data structures and metadata related to artists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Error Type Prediction

    No Comments

    Negative Logits
     Farr
    -0.61
     Irvin
    -0.58
     Lockwood
    -0.58
     Schweitzer
    -0.58
     Guzman
    -0.58
     Kelle
    -0.57
     McMillan
    -0.57
     Muller
    -0.56
     Schro
    -0.56
     Guilford
    -0.54
    POSITIVE LOGITS
     Ginn
    0.61
     Barna
    0.60
     Schaefer
    0.56
     Hawthorne
    0.55
     Giordano
    0.54
     Kaspar
    0.54
     Lennox
    0.53
     Clow
    0.53
     Dore
    0.52
     Argos
    0.52
    Activations Density 3.280%

    No Known Activations