© 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. 41-GEMMASCOPE-RES-16K
    11. 13567
    Prev
    Next
    INDEX
    Explanations

    programmatic elements related to software licensing and copyright terms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Pats
    -0.80
     sims
    -0.79
     cols
    -0.78
    cols
    -0.75
     mags
    -0.73
     dims
    -0.73
     meds
    -0.72
     grads
    -0.72
     secs
    -0.71
     docs
    -0.71
    POSITIVE LOGITS
    transmitters
    0.40
     Normdatei
    0.40
     Williams
    0.40
    onucleotides
    0.40
     advertisements
    0.40
     MainAxisSize
    0.39
     examinations
    0.39
    enschaften
    0.39
    ostructures
    0.39
    parameters
    0.38
    Activations Density 0.776%

    No Known Activations