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

    Neuronpedia

    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. 20-GEMMASCOPE-RES-16K
    11. 15058
    Prev
    Next
    INDEX
    Explanations

    instances of errors, particularly editorial and typographical mistakes, in written documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mistakes or errors

    np_acts-logits-general · gemini-2.0-flash

    errors and mistakes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    complexContent
    -0.75
    ThroughAttribute
    -0.56
    AnimationsModule
    -0.54
     noDo
    -0.50
    windowFixed
    -0.50
    EndGlobalSection
    -0.48
    isome
    -0.48
    TypedDataSet
    -0.47
    Demografía
    -0.47
     StatefulWidget
    -0.47
    POSITIVE LOGITS
     mistakes
    2.54
     errors
    2.38
     error
    2.26
     Mistakes
    2.24
     mistake
    2.23
     Errors
    2.04
     errores
    1.93
     Mistake
    1.93
     erreurs
    1.88
     Fehler
    1.88
    Activations Density 0.823%

    No Known Activations