© 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. 105369
    Prev
    Next
    INDEX
    Explanations

    specific terms related to biochemical processes and compounds

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    webElementGuid
    -0.60
    pulseira
    -0.56
     CallOverrides
    -0.52
     Autorisations
    -0.51
     EconPapers
    -0.50
    Uncertainty
    -0.49
    genodigd
    -0.49
     esfuer
    -0.48
    astéro
    -0.48
    writeFieldEnd
    -0.48
    POSITIVE LOGITS
    HandlerContext
    0.37
    MemoryWarning
    0.36
    ENOMEM
    0.33
    Enlaces
    0.30
    xase
    0.30
    tronics
    0.30
    ob
    0.30
    jgl
    0.29
    InjectMocks
    0.29
    bewerken
    0.28
    Activations Density 0.074%

    No Known Activations