© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101144
    Prev
    Next
    INDEX
    Explanations

    titles and roles of creative professionals and contributors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     pinulongan
    -0.50
     ProtoMessage
    -0.41
     gekocht
    -0.39
     competes
    -0.38
    必
    -0.38
     cuartos
    -0.37
     suel
    -0.36
    StoryboardSegue
    -0.36
     seguido
    -0.35
     deres
    -0.35
    POSITIVE LOGITS
     filmmaker
    0.78
     musician
    0.66
     novelist
    0.66
     journalist
    0.66
    businessman
    0.63
     dramatist
    0.63
     sculptor
    0.62
     businessman
    0.61
     surgeon
    0.60
    musician
    0.60
    Activations Density 0.017%

    No Known Activations