© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3018
    Prev
    Next
    INDEX
    Explanations

    expressions of curiosity or questioning thoughts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    the phrase "I wonder if" or similar speculative statements expressing uncertainty or curiosity.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou

    the phrase "I wonder" (and its variations like "wondered" or "wondering").

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @jyhe0408

    expressions of personal wondering or questioning, typically first-person statements indicating uncertainty or curiosity.

    oai_token-act-pair · gpt-5
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     lenker
    -0.38
    醐
    -0.37
    PhysRevD
    -0.37
    Bakgrunnsstoff
    -0.37
     sanitaires
    -0.35
     églises
    -0.35
    Batis
    -0.34
     esterni
    -0.34
    катерина
    -0.34
    Thick
    -0.33
    POSITIVE LOGITS
     Wonder
    0.96
     wonder
    0.96
    Wonder
    0.92
    wonder
    0.90
     WONDER
    0.89
     wonders
    0.76
     why
    0.66
     wondering
    0.66
     Wonders
    0.65
     Wander
    0.60
    Activations Density 0.092%

    No Known Activations