© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104794
    Prev
    Next
    INDEX
    Explanations

    the word "whatever" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Riau
    -0.50
    ⁃
    -0.49
     Cardano
    -0.47
    mml
    -0.46
    openqa
    -0.46
    sse
    -0.46
     Jiao
    -0.46
    DMC
    -0.46
     Diagnostics
    -0.45
    adaptiveStyles
    -0.44
    POSITIVE LOGITS
     whatever
    1.27
    whatever
    1.25
    Whatever
    1.16
     Whatever
    1.10
     whichever
    1.00
    atever
    0.95
     wherever
    0.89
    <bos>
    0.84
     whoever
    0.84
    Wherever
    0.75
    Activations Density 0.009%

    No Known Activations