© 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. 0-GEMMASCOPE-RES-16K
    11. 16088
    Prev
    Next
    INDEX
    Explanations

    patterns of frequency related to daily activities or behaviors

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    BeginContext
    -0.62
     sepol
    -0.57
    cydow
    -0.55
    astricht
    -0.54
     barnen
    -0.53
    canActivate
    -0.52
     polymorphism
    -0.51
     refirió
    -0.51
     polymorphisms
    -0.51
     dysplasia
    -0.51
    POSITIVE LOGITS
     weekly
    1.14
     daily
    1.07
    daily
    0.94
     monthly
    0.89
    Daily
    0.86
     Daily
    0.84
     täglichen
    0.83
    weekly
    0.83
     DAILY
    0.81
    Weekly
    0.80
    Activations Density 0.125%

    No Known Activations