© 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. 22-GEMMASCOPE-RES-16K
    11. 8184
    Prev
    Next
    INDEX
    Explanations

    terms related to CIA operations and intelligence activities

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

    CIA, intelligence, and espionage

    np_acts-logits-general · gemini-2.0-flash

    CIA intelligence officers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.79
    principalTable
    -0.59
    prepareStatement
    -0.58
     sindaco
    -0.57
    DeleteBehavior
    -0.56
    feitura
    -0.56
    webElementXpaths
    -0.56
    writel
    -0.54
     terapé
    -0.54
     GoFundMe
    -0.53
    POSITIVE LOGITS
     intelligence
    1.59
     Intelligence
    1.42
     CIA
    1.34
    intelligence
    1.33
    Intelligence
    1.32
     secret
    1.30
     spy
    1.24
     espionage
    1.18
     spies
    1.14
     covert
    1.13
    Activations Density 0.591%

    No Known Activations