© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 3332
    Prev
    Next
    INDEX
    Explanations

    references to the term "South" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMailer
    -0.88
     PKK
    -0.88
     Aleppo
    -0.83
     ویکی‌پدیای
    -0.80
     Kauai
    -0.79
     Ganes
    -0.79
     فريبيس
    -0.78
     وتسجيلات
    -0.76
     Kabul
    -0.75
     Dubuque
    -0.74
    POSITIVE LOGITS
     South
    3.13
    South
    2.90
     SOUTH
    2.60
    south
    2.55
    SOUTH
    2.52
     south
    2.51
    南
    1.63
     Zuid
    1.58
    Süd
    1.45
     南
    1.45
    Activations Density 0.067%

    No Known Activations