© 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. 102555
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "stir" and its variations

    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
    ⓧ
    -0.62
    Dakota
    -0.61
    mobileqq
    -0.60
     carbonic
    -0.59
     Canon
    -0.59
     Haag
    -0.58
     Goldberg
    -0.57
    Canon
    -0.57
    Gemeinden
    -0.57
    endregion
    -0.57
    POSITIVE LOGITS
     Stir
    0.76
    stir
    0.73
     stirring
    0.71
     stir
    0.68
    Stir
    0.67
     stirs
    0.63
     stirred
    0.61
     bailarina
    0.53
     meditación
    0.53
     navideños
    0.51
    Activations Density 0.004%

    No Known Activations