© 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 - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 11411
    Prev
    Next
    INDEX
    Explanations

    discussions around parental responsibilities and the dynamics of child-rearing

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

    having children

    np_acts-logits-general · gemini-2.0-flash

    having children

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dads
    -0.99
     dad
    -0.98
     Dad
    -0.92
     daddy
    -0.89
     mommy
    -0.88
     stepmother
    -0.86
     fathers
    -0.85
    Dad
    -0.84
     moms
    -0.82
     mom
    -0.81
    POSITIVE LOGITS
     children
    1.79
     child
    1.56
    children
    1.44
     kids
    1.40
     CHILDREN
    1.34
     enfants
    1.31
     Children
    1.30
    Children
    1.28
    child
    1.28
     chil
    1.20
    Activations Density 0.318%

    No Known Activations