© 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. 101011
    Prev
    Next
    INDEX
    Explanations

    negation words or phrases indicating something is not present or not applicable

    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
     courseId
    -0.55
    hsa
    -0.51
    ideas
    -0.50
     startX
    -0.50
    example
    -0.50
     isEnabled
    -0.49
     accountId
    -0.48
    riu
    -0.48
     célé
    -0.48
    idea
    -0.48
    POSITIVE LOGITS
    not
    0.99
     Not
    0.98
     not
    0.93
    Not
    0.92
     NOT
    0.86
    NOT
    0.84
    isNot
    0.78
     Notting
    0.71
     Nicht
    0.70
    Niet
    0.69
    Activations Density 0.024%

    No Known Activations