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. 20-GEMMASCOPE-RES-16K
    6. 12905
    Prev
    Next
    INDEX
    Explanations

    references to the consequences of U.S. interventions in foreign nations, particularly related to coups and dictatorial regimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    BufferException
    -0.56
    WaitGroup
    -0.55
    cesis
    -0.49
    XmlAttribute
    -0.47
     alemão
    -0.44
     Penns
    -0.44
    Obrázky
    -0.44
     AMA
    -0.44
     TNT
    -0.44
     jambes
    -0.44
    POSITIVE LOGITS
     dictator
    0.92
     dictators
    0.87
     ousted
    0.86
     deposed
    0.84
     regime
    0.83
     overthrown
    0.78
     authoritarian
    0.77
     coup
    0.76
     coups
    0.74
     dictatorship
    0.72
    Activations Density 0.311%

    No Known Activations