© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16342
    Prev
    Next
    INDEX
    Explanations

    references to South or Southern geographical locations

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

    Following "South" (often a country/region)

    np_acts-logits-general · gemini-2.0-flash

    "South" location names

    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
    )];
    -0.82
    isContained
    -0.76
     ویکی‌پدیای
    -0.75
    BindingResult
    -0.75
    ksikon
    -0.72
     للمعارف
    -0.68
    */),
    -0.65
    mbggenerated
    -0.65
     ModelExpression
    -0.65
     hObject
    -0.65
    POSITIVE LOGITS
    East
    0.60
    side
    0.59
     Carolina
    0.58
    wards
    0.57
     Africa
    0.57
     East
    0.55
     Korea
    0.54
     east
    0.53
    West
    0.52
    wester
    0.52
    Activations Density 0.111%

    No Known Activations