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

    Neuronpedia

    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. 4-GEMMASCOPE-RES-16K
    11. 1165
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dual" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lieber
    -0.80
     Muss
    -0.76
     guste
    -0.73
     bole
    -0.71
     Petru
    -0.70
    ope
    -0.70
     Mün
    -0.66
    xase
    -0.66
     financeira
    -0.66
     asiático
    -0.65
    POSITIVE LOGITS
     dual
    2.05
     Dual
    1.96
    Dual
    1.86
    dual
    1.83
     DUAL
    1.64
     duality
    0.81
     duel
    0.77
     twin
    0.72
    edal
    0.71
     Kombat
    0.71
    Activations Density 0.109%

    No Known Activations