© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 5872
    Prev
    Next
    INDEX
    Explanations

    instances of the word "then."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.93
     Monfieur
    -0.81
     itſelf
    -0.79
    ſelves
    -0.79
     ſeveral
    -0.79
     himſelf
    -0.77
     Cæsar
    -0.77
     Theſe
    -0.74
     ſame
    -0.73
     ſche
    -0.73
    POSITIVE LOGITS
     then
    4.95
    then
    3.94
     Then
    3.67
    Then
    3.61
     THEN
    3.51
     entonces
    3.20
    THEN
    3.11
     então
    3.01
     allora
    2.69
     dann
    2.66
    Activations Density 0.154%

    No Known Activations