© 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. 13-GEMMASCOPE-RES-16K
    11. 2291
    Prev
    Next
    INDEX
    Explanations

    references to institutional processes and accountability

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    createStatement
    -0.51
    
    -0.49
     Expansion
    -0.49
    生平
    -0.46
    dach
    -0.43
    testng
    -0.43
    DisplayMode
    -0.42
     cern
    -0.42
     Doh
    -0.41
     expansion
    -0.41
    POSITIVE LOGITS
     entrust
    0.78
     متعلقه
    0.73
     saites
    0.72
     trusts
    0.72
    KommentareTeilen
    0.71
     pinulongan
    0.70
     kwaliteit
    0.67
     jakość
    0.67
    QUALITY
    0.67
     vertrouwen
    0.66
    Activations Density 0.553%

    No Known Activations