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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 389
    Prev
    Next
    INDEX
    Explanations

    references to child-related and nutritional topics in data

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

    logical operators and function calls in programming contexts

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

    child or 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
    LabelTagHelper
    -0.71
     packing
    -0.49
     pack
    -0.48
     lace
    -0.48
    quese
    -0.48
     wax
    -0.48
     makers
    -0.47
     Raz
    -0.47
     Wax
    -0.47
     gom
    -0.46
    POSITIVE LOGITS
     child
    1.84
    child
    1.76
     children
    1.64
     Child
    1.64
     CHILD
    1.63
    Child
    1.59
    CHILD
    1.55
    children
    1.48
     CHILDREN
    1.48
     Children
    1.47
    Activations Density 0.041%

    No Known Activations