© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 10887
    Prev
    Next
    INDEX
    Explanations

    references to royalty, particularly related to queens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Queen followed by names or institutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tivoli
    -0.54
     Bronco
    -0.51
     Silas
    -0.50
    galus
    -0.49
     Eros
    -0.49
     Frisco
    -0.49
     Manus
    -0.48
     Menlo
    -0.47
     Ares
    -0.47
     Folsom
    -0.47
    POSITIVE LOGITS
     Queen
    2.05
    Queen
    2.03
     QUEEN
    1.90
     queen
    1.90
    queen
    1.74
    QUEEN
    1.62
     queens
    1.39
    queens
    1.36
    Queens
    1.32
     Queens
    1.31
    Activations Density 0.006%

    No Known Activations