© 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. 0-GEMMASCOPE-RES-16K
    11. 10576
    Prev
    Next
    INDEX
    Explanations

    terminology related to legal defense and defensive strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     refiere
    -0.45
     unregistered
    -0.44
    REQUEST
    -0.44
     arrivo
    -0.43
    önen
    -0.43
     gesprochen
    -0.43
     operated
    -0.43
     oper
    -0.43
     sesso
    -0.41
     terpisah
    -0.41
    POSITIVE LOGITS
     defense
    3.42
     defence
    3.19
     defenses
    2.90
     Defense
    2.82
    Defense
    2.81
     defend
    2.81
     defensive
    2.79
    defense
    2.77
     DEFENSE
    2.75
     defenders
    2.74
    Activations Density 0.110%

    No Known Activations