© 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. 20-GEMMASCOPE-RES-16K
    6. 3816
    Prev
    Next
    INDEX
    Explanations

    words related to demographic information and historical events

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

    Locations or groups in the Balkans

    np_acts-logits-general · gemini-2.0-flash

    Serbian people and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Assam
    -0.61
    RectangleBorder
    -0.60
     Eskimo
    -0.59
     Inuit
    -0.57
     PyTuple
    -0.53
     Mexiko
    -0.52
     Sentin
    -0.52
     Recife
    -0.51
     Guam
    -0.51
     Palmeiras
    -0.51
    POSITIVE LOGITS
     Serbian
    1.03
     Belgrade
    0.95
     Serbia
    0.94
     Serbs
    0.79
     Bosnia
    0.73
     Serb
    0.72
    Serbia
    0.72
    Ser
    0.72
     Serbie
    0.69
     Bos
    0.68
    Activations Density 0.063%

    No Known Activations