© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10996
    Prev
    Next
    INDEX
    Explanations

    mentions of geographic locations and associated demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Rhode Island and Odisha locations

    np_acts-logits-general · gemini-2.0-flash

    United States cities and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Himo
    -0.74
     himo
    -0.73
     Bourgoin
    -0.67
    IBarButtonItem
    -0.66
    expandindo
    -0.66
    ^(@)
    -0.62
    Borders
    -0.60
    הערות
    -0.60
    psack
    -0.58
    TagMode
    -0.56
    POSITIVE LOGITS
     Rhode
    0.64
    Rhode
    0.61
     Odisha
    0.59
    hubaneswar
    0.58
    contentLoaded
    0.52
     Orissa
    0.50
     Providence
    0.48
    Newport
    0.47
    Bari
    0.43
    nsito
    0.43
    Activations Density 0.074%

    No Known Activations