© 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. 18-GEMMASCOPE-RES-16K
    11. 437
    Prev
    Next
    INDEX
    Explanations

    events and actions related to conflict, violence, and military operations

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

    Prepositions followed by "enemies."

    np_acts-logits-general · gemini-2.0-flash

    enemies and conflict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.95
    VersionUID
    -0.74
    出版年
    -0.69
     surla
    -0.68
     للاسماء
    -0.68
    ChildScrollView
    -0.67
     nî
    -0.67
    HomeAsUpEnabled
    -0.65
    titleMargin
    -0.65
    ⓧ
    -0.63
    POSITIVE LOGITS
     enemy
    1.40
     enemies
    1.23
     opponents
    1.18
    enemy
    1.14
     opponent
    1.10
     foes
    1.05
     Enemy
    1.03
     adversaries
    1.03
     adversary
    1.02
     musuh
    1.02
    Activations Density 0.493%

    No Known Activations