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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8038
    Prev
    Next
    INDEX
    Explanations

    terms related to conviction or legal judgment

    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
     Theſe
    -0.90
     vaut
    -0.89
     ainfi
    -0.86
    IonicModule
    -0.85
     plais
    -0.80
    berdayakan
    -0.79
     hasard
    -0.77
    migrationBuilder
    -0.76
    ArrowToggle
    -0.76
     Efq
    -0.75
    POSITIVE LOGITS
    Con
    2.85
     Con
    2.82
    con
    2.58
     CON
    2.47
    CON
    2.43
     con
    2.08
     kon
    1.83
     Kon
    1.83
    Kon
    1.71
     cones
    1.66
    Activations Density 0.133%

    No Known Activations