© 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. 22-GEMMASCOPE-RES-16K
    11. 2702
    Prev
    Next
    INDEX
    Explanations

    instances of the word "then" indicating sequences or transitions in narratives

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

    Preceding a sequential action or event

    np_acts-logits-general · gemini-2.0-flash

    sequence of events or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -0.76
    ówczas
    -0.76
     damaligen
    -0.69
    Тогда
    -0.64
     alors
    -0.64
     itemprop
    -0.63
     entonces
    -0.62
     Тогда
    -0.61
    multer
    -0.61
    tedy
    -0.60
    POSITIVE LOGITS
     lintas
    0.77
     followed
    0.77
     they
    0.76
     proceeded
    0.73
     we
    0.72
     comes
    0.71
     proceed
    0.70
     EconPapers
    0.69
    followed
    0.68
     later
    0.68
    Activations Density 0.115%

    No Known Activations