© 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. 3-GEMMASCOPE-RES-16K
    11. 11677
    Prev
    Next
    INDEX
    Explanations

    terms related to design and invention

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     размере
    -0.45
     arkiv
    -0.41
    quelle
    -0.41
     knji
    -0.38
    tagez
    -0.38
     έκ
    -0.37
     보고
    -0.37
     kiek
    -0.36
     workforce
    -0.36
     iyon
    -0.36
    POSITIVE LOGITS
     manufactured
    1.93
     crafted
    1.89
     constructed
    1.84
     engineered
    1.70
    manufactured
    1.66
     fabricated
    1.64
    Manufactured
    1.61
     designed
    1.56
    constructed
    1.54
     Manufactured
    1.50
    Activations Density 0.307%

    No Known Activations