© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104959
    Prev
    Next
    INDEX
    Explanations

    terms related to population studies and institutional affiliations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ujednoznacz
    -0.70
     surla
    -0.66
    Tikang
    -0.64
    Datuak
    -0.56
    staaten
    -0.53
    rungsseite
    -0.51
    httphttps
    -0.51
    GEBURTSDATUM
    -0.50
     المعيارى
    -0.50
     states
    -0.49
    POSITIVE LOGITS
    𝟸
    0.47
     downtown
    0.44
     Restaurants
    0.42
    Spectrum
    0.42
     Downtown
    0.41
     mayoral
    0.40
     useSelector
    0.40
    thoven
    0.39
     pajero
    0.39
     Rector
    0.39
    Activations Density 0.143%

    No Known Activations