© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 4470
    Prev
    Next
    INDEX
    Explanations

    references to societal and cultural trends

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    shtml
    -0.68
     cervello
    -0.66
     maîtrise
    -0.63
     chiếc
    -0.62
     lettore
    -0.61
    rasp
    -0.61
    PSL
    -0.59
     infancia
    -0.57
     Madsen
    -0.57
    客室
    -0.57
    POSITIVE LOGITS
     trend
    3.62
     trends
    3.47
     Trend
    3.18
    Trend
    2.97
    trend
    2.95
     Trends
    2.94
    trends
    2.77
    Trends
    2.76
     TRENDS
    2.64
     trending
    2.48
    Activations Density 0.040%

    No Known Activations