© 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. 20-GEMMASCOPE-RES-16K
    11. 12020
    Prev
    Next
    INDEX
    Explanations

    terms related to national security and military strategies

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

    Geopolitics, diplomacy, security

    np_acts-logits-general · gemini-2.0-flash

    international politics and foreign 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
    муля
    -0.47
    ulte
    -0.44
     expéri
    -0.43
     memb
    -0.42
     Millions
    -0.42
    tomie
    -0.42
     Recreational
    -0.40
    る
    -0.40
     TORONTO
    -0.40
     Ontario
    -0.39
    POSITIVE LOGITS
     geopolitical
    1.21
     foreign
    1.04
     diplomacy
    1.04
     Foreign
    1.01
     geo
    0.98
     security
    0.98
     Diplomacy
    0.96
    Foreign
    0.94
     diplomatic
    0.91
     Security
    0.88
    Activations Density 0.289%

    No Known Activations