© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14045
    Prev
    Next
    INDEX
    Explanations

    references to small, rural communities or villages

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

    Followed by "town" or "village"

    np_acts-logits-general · gemini-2.0-flash

    small towns and villages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Istanbul
    -0.51
     Lisbon
    -0.50
     Mumbai
    -0.50
     İstanbul
    -0.50
     Luanda
    -0.49
    Amsterdam
    -0.48
     Amsterdam
    -0.48
    Nairobi
    -0.46
     Karachi
    -0.45
     Lisboa
    -0.45
    POSITIVE LOGITS
     town
    1.58
     village
    1.56
     towns
    1.42
     villages
    1.27
    village
    1.27
     small
    1.17
    小镇
    1.08
     hamlet
    1.07
     TOWN
    1.07
    small
    1.05
    Activations Density 0.263%

    No Known Activations