© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1063
    Prev
    Next
    INDEX
    Explanations

    references to children and child-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.91
    WriteLiteral
    -0.74
    etera
    -0.73
     Weinstein
    -0.72
     commissioners
    -0.71
     Commissioners
    -0.71
     peeps
    -0.70
    People
    -0.70
     Frenchmen
    -0.70
     Ripley
    -0.69
    POSITIVE LOGITS
     Child
    2.06
     child
    2.03
     CHILD
    1.87
    Child
    1.81
    child
    1.72
    CHILD
    1.69
     Childs
    1.37
     childs
    1.36
    childs
    1.33
    getChild
    0.91
    Activations Density 0.084%

    No Known Activations