© 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. 13-GEMMASCOPE-RES-16K
    11. 10584
    Prev
    Next
    INDEX
    Explanations

    terms related to weaponry and military

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OrNil
    -0.97
    CloseOperation
    -0.93
    theless
    -0.92
    mallows
    -0.88
     Malt
    -0.80
     QH
    -0.80
    tificates
    -0.80
     виправивши
    -0.80
     PPM
    -0.79
    OOOOOOOO
    -0.79
    POSITIVE LOGITS
     Bed
    0.80
    beds
    0.77
     BED
    0.76
     Arm
    0.75
    Bed
    0.75
     Beds
    0.74
     Kings
    0.74
    a
    0.73
     arm
    0.72
    bed
    0.71
    Activations Density 0.103%

    No Known Activations