© 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. 1414
    Prev
    Next
    INDEX
    Explanations

    indicators of child health and development metrics

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

    terms related to measuring children's health metrics

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

    growth and height

    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
     colitis
    -0.48
     <=",
    -0.48
     للمعارف
    -0.48
     lacri
    -0.46
     conjun
    -0.46
     שוליים
    -0.45
     redness
    -0.45
     tears
    -0.45
     lupus
    -0.45
     ujednoznacz
    -0.44
    POSITIVE LOGITS
     Growth
    1.11
     growth
    1.09
    Growth
    1.06
    growth
    1.01
     GROWTH
    0.93
     height
    0.87
     stunted
    0.84
    GROW
    0.83
     Height
    0.83
     stature
    0.83
    Activations Density 0.511%

    No Known Activations