© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 141
    Prev
    Next
    INDEX
    Explanations

    terms related to military enlistment and service

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

    mentions of military service and enlistment

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

    the military

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     NgModule
    -0.53
    ibrator
    -0.50
    AxisSize
    -0.49
    ]")]
    -0.49
    steria
    -0.47
    rmtree
    -0.45
    oxane
    -0.45
    chale
    -0.45
    XmlAccessType
    -0.43
    interopRequire
    -0.43
    POSITIVE LOGITS
     army
    1.45
     Army
    1.28
     Navy
    1.20
     navy
    1.17
    Army
    1.13
    army
    1.10
     armies
    1.05
     force
    1.05
     Force
    1.05
     Armed
    1.03
    Activations Density 0.186%

    No Known Activations