© 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. 8396
    Prev
    Next
    INDEX
    Explanations

    terms related to military operations and deployments

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

    Military deployments or missions

    np_acts-logits-general · gemini-2.0-flash

    military deployment and missions

    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
     تضيفلها
    -0.70
     propOrder
    -0.67
    enumi
    -0.66
     للاسماء
    -0.66
    hasMoreElements
    -0.60
    évaluateur
    -0.60
     OFDb
    -0.59
    rungsseite
    -0.58
     виправивши
    -0.57
    Parameteri
    -0.56
    POSITIVE LOGITS
     missions
    1.21
     mission
    1.18
     deployment
    1.01
     deployments
    0.99
     Missions
    0.97
    Missions
    0.93
    mission
    0.92
     deployed
    0.91
     missione
    0.91
     Mission
    0.91
    Activations Density 0.154%

    No Known Activations