© 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 - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 2894
    Prev
    Next
    INDEX
    Explanations

    the word "way" indicating direction or progress

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    aarrggbb
    -0.78
    XmlAccessType
    -0.71
    setVerticalGroup
    -0.70
    IntoConstraints
    -0.68
     otomatig
    -0.67
    awtextra
    -0.65
     للاسماء
    -0.65
    :✨
    -0.63
     zijne
    -0.63
    AccessorTable
    -0.62
    POSITIVE LOGITS
     reflection
    0.83
    Reflection
    0.80
     Reflection
    0.73
     Reflect
    0.69
    reflect
    0.68
     reflect
    0.66
    Reflect
    0.65
    reflection
    0.63
     mirror
    0.60
     reflecting
    0.60
    Activations Density 0.122%

    No Known Activations