© 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. 20-GEMMASCOPE-RES-16K
    11. 14984
    Prev
    Next
    INDEX
    Explanations

    events involving interruptions or distractions in conversations

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

    Someone interrupting or being interrupted

    np_acts-logits-general · gemini-2.0-flash

    actions interrupting or continuing

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     weekends
    -0.67
     Monthly
    -0.65
     monthly
    -0.64
     Nowadays
    -0.59
     overnight
    -0.59
    days
    -0.58
    Monthly
    -0.58
     winters
    -0.58
     ligiloj
    -0.58
    Overnight
    -0.56
    POSITIVE LOGITS
     momentarily
    0.75
     visibly
    0.72
     applau
    0.71
     loudly
    0.71
     audible
    0.71
     fidget
    0.69
     mikrofon
    0.68
     seated
    0.66
     whispered
    0.66
     everyone
    0.65
    Activations Density 0.575%

    No Known Activations