© 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. 33-GEMMASCOPE-RES-16K
    11. 3515
    Prev
    Next
    INDEX
    Explanations

    specific dates, events, and personal actions or achievements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     actuellement
    -0.70
     recent
    -0.69
     teraz
    -0.68
     obecnie
    -0.68
     later
    -0.68
    今後も
    -0.68
     ngayon
    -0.68
     später
    -0.67
     sekarang
    -0.67
     תמיד
    -0.66
    POSITIVE LOGITS
     accidentally
    0.63
     unexpectedly
    0.62
     suddenly
    0.60
     disambiguazione
    0.59
     announced
    0.58
     officially
    0.57
     formally
    0.57
     ceremon
    0.56
     visited
    0.52
     embarked
    0.52
    Activations Density 0.602%

    No Known Activations