© 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. 15060
    Prev
    Next
    INDEX
    Explanations

    the word "then" or its variations indicating a sequence of events

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

    "Then" followed by a subsequent clause

    np_acts-logits-general · gemini-2.0-flash

    then

    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
    ówczas
    -0.77
     then
    -0.67
     ferons
    -0.66
    tedy
    -0.66
     damaligen
    -0.64
     firebaseConfig
    -0.64
     GenerationType
    -0.63
    Тогда
    -0.63
     Тогда
    -0.61
    {}{}
    -0.61
    POSITIVE LOGITS
    addGap
    0.74
     مرئيه
    0.73
     lintas
    0.73
     gynhyrchwyd
    0.67
     EconPapers
    0.66
     there
    0.65
     they
    0.65
     maybe
    0.61
    ew
    0.59
    ians
    0.59
    Activations Density 0.106%

    No Known Activations