© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 12498
    Prev
    Next
    INDEX
    Explanations

    terms related to reconnaissance and surveillance activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataAnnotations
    -0.77
    TemporalType
    -0.74
    ImageContext
    -0.71
    ValueStyle
    -0.70
     TextAlign
    -0.70
    InputTagHelper
    -0.68
    astify
    -0.68
    tonsoft
    -0.68
    quelize
    -0.67
    ArgsConstructor
    -0.67
    POSITIVE LOGITS
     suspicious
    1.05
     spying
    0.97
     spion
    0.95
     spy
    0.94
     spied
    0.90
     scouting
    0.87
     spies
    0.87
     surveillance
    0.86
    spy
    0.85
     suspicion
    0.84
    Activations Density 0.300%

    No Known Activations