© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 720
    Prev
    Next
    INDEX
    Explanations

    references to family dynamics and parenting in the context of interfaith relationships

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

    references to discussions about future plans and family in relationships

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

    have children

    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
    contentLoaded
    -0.63
    Datuak
    -0.55
    protoimpl
    -0.50
    ″]
    -0.49
    thansa
    -0.46
    ähle
    -0.46
    出版年
    -0.45
    ":"",
    -0.44
     Enix
    -0.44
    AuthContext
    -0.43
    POSITIVE LOGITS
     children
    2.30
     kids
    2.18
    children
    1.97
     Children
    1.89
    kids
    1.89
    Children
    1.87
     CHILDREN
    1.80
     Kids
    1.79
    Kids
    1.77
     enfants
    1.73
    Activations Density 0.292%

    No Known Activations