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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10550
    Prev
    Next
    INDEX
    Explanations

    locations and place names in urban contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     religiosas
    -0.56
    ANTLR
    -0.55
    mogat
    -0.54
    oluciones
    -0.53
     defaultValue
    -0.52
    éraire
    -0.52
     religieuses
    -0.50
     raisonnable
    -0.49
    antren
    -0.49
    Rujukan
    -0.48
    POSITIVE LOGITS
     Midtown
    0.76
    martre
    0.76
    Downtown
    0.72
     downtown
    0.69
     Downtown
    0.67
    cadilly
    0.66
     Soho
    0.62
     Covent
    0.62
    Manhattan
    0.61
     Manhattan
    0.61
    Activations Density 1.317%

    No Known Activations