© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3488
    Prev
    Next
    INDEX
    Explanations

    references to maternal figures or the concept of motherhood

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

    mother and father figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ized
    -0.82
    ised
    -0.71
    ed
    -0.68
    ization
    -0.61
    naires
    -0.61
    izing
    -0.61
    fully
    -0.60
    a
    -0.60
    isations
    -0.60
    ه
    -0.58
    POSITIVE LOGITS
     dads
    0.89
     DAD
    0.79
    Dad
    0.77
     dad
    0.75
     MOM
    0.74
     Dad
    0.73
     Charlemagne
    0.71
     mom
    0.70
     moms
    0.70
    Mom
    0.68
    Activations Density 0.013%

    No Known Activations