© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6969
    Prev
    Next
    INDEX
    Explanations

    references to "Lady" in various contexts

    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
    تقاوى
    -0.82
    ]){
    
    -0.77
    ]))
    
    -0.74
    ศาสตร์
    -0.71
    jetunion
    -0.69
    ]));
    
    -0.69
     archipelago
    -0.69
    uyla
    -0.69
     quoi
    -0.66
    seamnă
    -0.66
    POSITIVE LOGITS
     Lady
    2.92
     lady
    2.91
     LADY
    2.86
    Lady
    2.73
    lady
    2.54
    LADY
    2.47
     ladies
    2.30
     Ladies
    2.17
    ladies
    2.07
    Ladies
    1.90
    Activations Density 0.099%

    No Known Activations