© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 3738
    Prev
    Next
    INDEX
    Explanations

    references to military organizations, specifically the Army and Navy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fides
    -0.78
     Strut
    -0.69
    chere
    -0.64
    BrowserModule
    -0.63
     Fok
    -0.63
    tyfik
    -0.63
    ondheim
    -0.63
     Bitch
    -0.62
    NOPQRST
    -0.62
    BITE
    -0.62
    POSITIVE LOGITS
     Army
    2.91
     army
    2.62
    Army
    2.59
    army
    2.34
     ARMY
    2.29
     armies
    1.91
     Armies
    1.76
     Armee
    1.56
     ejército
    1.47
    armée
    1.45
    Activations Density 0.042%

    No Known Activations