© 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. 104890
    Prev
    Next
    INDEX
    Explanations

    positive adjectives that convey high praise or admiration

    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
     Inscrivez
    -0.52
     problemet
    -0.46
     fallait
    -0.45
     veuillez
    -0.44
     avoient
    -0.42
     miniaturka
    -0.42
     littéraire
    -0.42
     Produits
    -0.41
     judicia
    -0.41
     vectorielle
    -0.41
    POSITIVE LOGITS
     समीक्षाओं
    0.54
    存于互联网档案馆
    0.53
     ddelweddau
    0.49
    Datuak
    0.45
     propOrder
    0.43
    malink
    0.43
     dune
    0.42
    帖最后由
    0.42
    tissimi
    0.42
     lovely
    0.42
    Activations Density 0.021%

    No Known Activations