© 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. 9304
    Prev
    Next
    INDEX
    Explanations

    words associated with popping, blinking, or bouncing actions

    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
    gameserver
    -0.44
    Requ
    -0.43
     dest
    -0.43
     Requ
    -0.42
     dyr
    -0.40
    typeorm
    -0.36
     VII
    -0.35
    壌
    -0.34
     Principal
    -0.34
     requ
    -0.34
    POSITIVE LOGITS
     popping
    0.82
     Bounce
    0.77
     pinulongan
    0.75
     pop
    0.72
     twinkle
    0.71
    Bounce
    0.69
     popped
    0.68
     bounce
    0.67
     blink
    0.66
     twinkling
    0.64
    Activations Density 0.243%

    No Known Activations