© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 16240
    Prev
    Next
    INDEX
    Explanations

    elements related to international relations and geopolitical tensions

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

    Acts of military aggression and violence

    np_acts-logits-general · gemini-2.0-flash

    actions of war and violence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hely
    -0.53
     asiatique
    -0.52
     δύ
    -0.51
    ülé
    -0.50
    GEBURTSDATUM
    -0.50
    #
    -0.49
     africaine
    -0.48
     binomial
    -0.47
    getPost
    -0.47
    pholes
    -0.47
    POSITIVE LOGITS
     massac
    0.84
     invaded
    0.80
     attacked
    0.76
     exter
    0.75
     invade
    0.75
     bombed
    0.72
     overrun
    0.70
     slaughtered
    0.70
     kidnapped
    0.66
     perse
    0.66
    Activations Density 0.484%

    No Known Activations