© 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. 1347
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly in entertainment or celebrity contexts

    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
     “
    -0.50
      
    -0.50
     "
    -0.49
     A
    -0.49
    ,
    -0.47
     
    -0.47
    ↵
    -0.47
    ↵↵
    -0.46
    addContainerGap
    -0.44
     au
    -0.44
    POSITIVE LOGITS
     ModelExpression
    1.05
     korean
    0.95
     Seoul
    0.94
     Koreans
    0.94
     Korean
    0.91
     korea
    0.90
    Korean
    0.89
     Busan
    0.88
     Korea
    0.88
    Seoul
    0.85
    Activations Density 1.636%

    No Known Activations