© 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. 2758
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons or references to measurements above a certain threshold

    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
     mariage
    -0.41
     âge
    -0.41
     espont
    -0.39
     dîner
    -0.38
    ArgsConstructor
    -0.38
     zelve
    -0.36
     således
    -0.36
     okuyayım
    -0.36
    новништво
    -0.36
     disambiguazione
    -0.36
    POSITIVE LOGITS
     Above
    1.26
    Above
    1.17
     ABOVE
    1.03
     Below
    1.02
     above
    1.02
    above
    0.96
     beyond
    0.94
    Below
    0.91
    ABOVE
    0.91
     below
    0.87
    Activations Density 0.107%

    No Known Activations