© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10685
    Prev
    Next
    INDEX
    Explanations

    information related to early childhood development and milestones

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

    Child development and care

    np_acts-logits-general · gemini-2.0-flash

    age milestones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jugendlichen
    -0.54
     arşivlendi
    -0.53
     Adoles
    -0.52
     Jugendliche
    -0.52
     Teens
    -0.50
     adolescent
    -0.49
    adoles
    -0.49
     teens
    -0.49
     cadet
    -0.49
     adolescents
    -0.48
    POSITIVE LOGITS
     toddler
    1.16
     toddlers
    1.09
     Toddler
    0.97
    toddler
    0.96
     infant
    0.93
     preschool
    0.93
     infants
    0.92
     babies
    0.88
     baby
    0.88
     Preschool
    0.87
    Activations Density 0.149%

    No Known Activations