© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 13449
    Prev
    Next
    INDEX
    Explanations

    locations, specifically names of places and associated geographical entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoField
    -0.79
    GEBURTSDATUM
    -0.69
    TagMode
    -0.61
    InjectAttribute
    -0.57
     TextAppearance
    -0.55
    ajs
    -0.55
     publiés
    -0.54
    GIH
    -0.54
     AssemblyTitle
    -0.52
    CharStream
    -0.52
    POSITIVE LOGITS
     Dakota
    0.80
     Bismarck
    0.79
     Fargo
    0.77
     Sioux
    0.73
    Dakota
    0.72
     Winnipeg
    0.68
    Winnipeg
    0.63
     Yank
    0.63
     Manitoba
    0.62
     ND
    0.61
    Activations Density 0.145%

    No Known Activations