© 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. 105268
    Prev
    Next
    INDEX
    Explanations

    references to historical or mythological figures, particularly focusing on their relationships and lineage

    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
    parsedMessage
    -0.79
     intptr
    -0.75
    addGap
    -0.71
    ConstraintMaker
    -0.70
     mergeFrom
    -0.67
    featureID
    -0.66
     protoimpl
    -0.64
    msgTypes
    -0.57
    addPreferredGap
    -0.55
     CreateTagHelper
    -0.54
    POSITIVE LOGITS
     serez
    0.46
     professionnelle
    0.42
     réservé
    0.41
     recevrez
    0.40
     particuliers
    0.40
     professionale
    0.39
     présence
    0.38
     trouverez
    0.38
     Talent
    0.37
    Talent
    0.37
    Activations Density 0.001%

    No Known Activations