© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14154
    Prev
    Next
    INDEX
    Explanations

    instances of bullying and social struggles in a school setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Autoritní
    -0.48
     bedrijven
    -0.42
     nacht
    -0.41
     vermogen
    -0.39
     reizen
    -0.38
    ท่าน
    -0.37
     voorbij
    -0.36
     poffible
    -0.35
     contracting
    -0.34
    hörige
    -0.34
    POSITIVE LOGITS
     classmates
    0.77
     girls
    0.69
     classmate
    0.67
     bullying
    0.66
     bullies
    0.66
     boys
    0.65
     school
    0.64
    girls
    0.63
     bullied
    0.62
     bully
    0.61
    Activations Density 0.116%

    No Known Activations