Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1155
    Prev
    Next
    INDEX
    Explanations

    references to Uganda and its historical context, particularly related to events involving its leadership and the local population

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

    Uganda, Ugandan, or related to Uganda

    np_acts-logits-general · gemini-2.0-flash

    Uganda and related topics

    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
    PyExc
    -0.52
     pyplot
    -0.52
    inaison
    -0.52
     gọn
    -0.51
     المعيارى
    -0.51
     forKey
    -0.50
    DockStyle
    -0.49
    usters
    -0.49
    RectangleBorder
    -0.49
    XMLSchema
    -0.49
    POSITIVE LOGITS
     Uganda
    0.78
     Kampala
    0.69
     Ugandan
    0.68
     Ente
    0.64
    Uganda
    0.64
    ">//
    0.63
     AssemblyCulture
    0.59
     Ky
    0.56
    Ky
    0.53
     vulgares
    0.52
    Activations Density 0.055%

    No Known Activations