© 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 - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 12333
    Prev
    Next
    INDEX
    Explanations

    references to parentage and citizenship status, particularly in legal contexts concerning children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Son
    -0.73
     hijos
    -0.67
    son
    -0.67
    SON
    -0.66
     Son
    -0.64
     grandson
    -0.63
     figlio
    -0.63
     grandchildren
    -0.63
     granddaughter
    -0.63
    弟子
    -0.62
    POSITIVE LOGITS
     dad
    1.82
     father
    1.72
     parent
    1.71
     mom
    1.71
     Dad
    1.67
     parents
    1.66
     mother
    1.60
    Dad
    1.58
     daddy
    1.57
    father
    1.54
    Activations Density 0.319%

    No Known Activations