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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 12913
    Prev
    Next
    INDEX
    Explanations

    details related to political events and individuals involved in conflicts

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

    East African countries

    np_acts-logits-general · gemini-2.0-flash

    Uganda, Rwanda, Burundi, Finland

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.55
    batore
    -0.49
    ⓧ
    -0.49
     Texans
    -0.49
    ímos
    -0.45
    الدراسه
    -0.45
     retirada
    -0.43
    indre
    -0.42
     réelle
    -0.42
    ynos
    -0.42
    POSITIVE LOGITS
     Uganda
    0.87
    зулта
    0.86
     Ugandan
    0.77
     Kampala
    0.73
    Uganda
    0.72
    PerformLayout
    0.72
    MessageOf
    0.71
    Rwanda
    0.70
     AttributeSet
    0.69
     Ente
    0.68
    Activations Density 0.036%

    No Known Activations