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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 8035
    Prev
    Next
    INDEX
    Explanations

    references to covert operations and the involvement of the CIA

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    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
    -1.01
     />";
    -0.62
    Aspiration
    -0.61
    elemField
    -0.61
    VersionUID
    -0.60
    />";
    -0.59
     krzy
    -0.59
    feitura
    -0.59
    AnimationsModule
    -0.58
    otypic
    -0.57
    POSITIVE LOGITS
     intelligence
    1.26
     Intelligence
    1.16
     CIA
    1.16
     espionage
    1.14
     spy
    1.12
    Intelligence
    1.07
    intelligence
    1.00
     spies
    0.97
     secret
    0.97
    CIA
    0.93
    Activations Density 0.546%

    No Known Activations