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. 14819
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical tensions, particularly involving Iran, Russia, and nuclear issues

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

    Tensions with countries/entities

    np_acts-logits-general · gemini-2.0-flash

    countries and geopolitical relations

    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
    TagMode
    -0.77
    Istorija
    -0.58
    kmäler
    -0.55
    Cancelable
    -0.54
    afficheront
    -0.53
    Gemeinden
    -0.51
     Waray
    -0.49
    etus
    -0.48
     setError
    -0.48
     trimester
    -0.48
    POSITIVE LOGITS
     Iranian
    0.72
     Irán
    0.71
     Iran
    0.71
     Xi
    0.68
     cinese
    0.66
     Hezbollah
    0.64
     Tehran
    0.61
    Iranian
    0.60
     chinoise
    0.60
     iran
    0.59
    Activations Density 0.143%

    No Known Activations