© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 116768
    Prev
    Next
    INDEX
    Explanations

    the word "of" in various contexts, indicating an emphasis on relationships or connections

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     húmedo
    -0.41
     alguno
    -0.37
     ouders
    -0.37
     moeite
    -0.35
     sorpresas
    -0.35
    ม้
    -0.34
     elä
    -0.33
     costumbres
    -0.33
     rencontr
    -0.33
    BufferException
    -0.33
    POSITIVE LOGITS
    EnableWeb
    0.68
    adaptiveStyles
    0.63
     kaarangay
    0.63
    RenderAtEndOf
    0.61
     TextAppearance
    0.59
    sedown
    0.58
    pylene
    0.58
     iſt
    0.57
    Jeografia
    0.57
    ſche
    0.56
    Activations Density 0.006%

    No Known Activations