© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8251
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical power dynamics and actions involving specific nations

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

    before or related to geopolitical strategy

    np_acts-logits-general · gemini-2.0-flash

    geopolitical strategy and influence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TRIBUN
    -0.39
     Bool
    -0.37
    nesota
    -0.35
    LLocation
    -0.34
     Pet
    -0.33
     souvenirs
    -0.33
     محفوظة
    -0.32
    +#+
    -0.32
     Pseud
    -0.32
     soud
    -0.32
    POSITIVE LOGITS
     geopolitical
    0.69
    MLLoader
    0.66
     strategically
    0.65
     régionale
    0.62
     strategic
    0.61
     destabili
    0.60
     alliances
    0.60
     regionally
    0.59
     regional
    0.57
     estratégica
    0.57
    Activations Density 0.352%

    No Known Activations