© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 5287
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pretty" 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 @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NgModule
    -0.58
    }{*}{}
    -0.54
    ाहरण
    -0.53
    IsContent
    -0.52
    ыре
    -0.50
     peores
    -0.49
    ится
    -0.49
     Wonders
    -0.49
    TintMode
    -0.48
    errHandler
    -0.48
    POSITIVE LOGITS
     much
    1.51
    much
    1.27
     darn
    1.18
    Much
    1.16
     Much
    1.08
     damn
    0.92
     MUCH
    0.86
     pretty
    0.85
     decent
    0.76
     damned
    0.75
    Activations Density 0.037%

    No Known Activations