© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 38319
    Prev
    Next
    INDEX
    Explanations

    references to divorce, including its grounds and legal implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astien
    -0.82
     SHEET
    -0.75
    Viitteet
    -0.71
     Sheets
    -0.69
    +#+#
    -0.69
    ordinator
    -0.68
     Yat
    -0.68
     Striker
    -0.68
     Sheet
    -0.67
    chymal
    -0.67
    POSITIVE LOGITS
     divorce
    1.57
    Divorce
    1.48
     Divorce
    1.48
     divor
    1.43
    orced
    1.40
     divorced
    1.23
    orce
    1.00
     matrimon
    0.81
    FFIX
    0.77
    离婚
    0.75
    Activations Density 0.007%

    No Known Activations