© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12503
    Prev
    Next
    INDEX
    Explanations

    concepts related to marriage and family structure

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

    references to marriage and family structure—especially traditional/heteronormative or religious (temple/eternal family) contexts involving parents and children

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    references to traditional marriage between a man and a woman, particularly in religious or conservative contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oneofs
    -0.41
     peeled
    -0.40
    暗
    -0.39
    TintMode
    -0.39
    marked
    -0.38
    mete
    -0.38
     vibe
    -0.37
     transf
    -0.36
    pova
    -0.36
     Aristi
    -0.36
    POSITIVE LOGITS
     marriage
    0.61
     Family
    0.60
     famiglie
    0.59
     marriages
    0.57
     Marriage
    0.57
     families
    0.57
     family
    0.56
     csalá
    0.55
    ArgsConstructor
    0.55
    prepareStatement
    0.54
    Activations Density 0.427%

    No Known Activations