© 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. 2-GEMMASCOPE-RES-16K
    11. 490
    Prev
    Next
    INDEX
    Explanations

    references to mathematical notations or symbols

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    הפ
    -0.38
     הפ
    -0.33
     pos
    -0.31
     gustado
    -0.30
    jewództ
    -0.30
     transfieras
    -0.29
     הפר
    -0.29
     pa
    -0.28
    ила
    -0.28
     pol
    -0.27
    POSITIVE LOGITS
    Pu
    0.93
    Pi
    0.91
     Put
    0.91
     Pu
    0.91
     Pen
    0.90
     Pad
    0.89
    Pen
    0.88
     Pas
    0.87
    Pin
    0.87
    Pe
    0.86
    Activations Density 0.589%

    No Known Activations