© 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. 3-GEMMASCOPE-RES-16K
    11. 9738
    Prev
    Next
    INDEX
    Explanations

    instances of the word "though" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -1.07
    :✨
    -0.96
     Cæsar
    -0.93
     cdti
    -0.89
     myſelf
    -0.88
    Демографія
    -0.84
    Amicalement
    -0.83
     $_"
    -0.81
     Monfieur
    -0.79
     itſelf
    -0.78
    POSITIVE LOGITS
     though
    0.95
     when
    0.90
     if
    0.89
     because
    0.88
     “
    0.80
     the
    0.76
     although
    0.75
    <strong>
    0.73
    (
    0.73
    “
    0.73
    Activations Density 0.063%

    No Known Activations