© 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. 1-GEMMASCOPE-RES-16K
    11. 7220
    Prev
    Next
    INDEX
    Explanations

    terms related to war and military conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disiplin
    -0.59
     Piemonte
    -0.56
     iconFacebook
    -0.55
    cshtml
    -0.54
    ITHUB
    -0.54
     незавершена
    -0.53
     inderdaad
    -0.52
     redaktion
    -0.52
     citoy
    -0.52
    CloseOperation
    -0.52
    POSITIVE LOGITS
     war
    4.37
     War
    4.21
    war
    4.11
    War
    4.01
     WAR
    3.63
    WAR
    3.45
     wars
    2.73
     guerra
    2.62
    wars
    2.35
     guerre
    2.32
    Activations Density 0.049%

    No Known Activations