© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101976
    Prev
    Next
    INDEX
    Explanations

    instances of the word "why" indicating questioning or reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    UCC
    -0.50
     DSS
    -0.49
     DRS
    -0.49
     GSC
    -0.49
    IMC
    -0.49
     colla
    -0.48
     Golem
    -0.47
     IMC
    -0.47
     Table
    -0.46
     table
    -0.44
    POSITIVE LOGITS
     why
    1.23
    why
    1.16
    Why
    1.14
     Why
    1.10
     WHY
    1.09
    WHY
    1.05
     Pourquoi
    1.01
    Pourquoi
    0.98
     Whyte
    0.97
     Waarom
    0.93
    Activations Density 0.014%

    No Known Activations