© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 516
    Prev
    Next
    INDEX
    Explanations

    punctuations and formatting indicators in the text

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

    dots that signal the end of a sentence or statement

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

    Mvvm and URLs

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     nakalista
    -0.62
    WaitGroup
    -0.60
    SourceChecksum
    -0.59
    Filmografia
    -0.58
    opis
    -0.56
    devtool
    -0.56
     developed
    -0.56
    EndContext
    -0.56
    isDebugEnabled
    -0.55
    currentColor
    -0.53
    POSITIVE LOGITS
     myſelf
    1.01
     houſe
    0.96
     Diſ
    0.94
     Houſe
    0.93
     themſelves
    0.90
     itſelf
    0.87
     Inſ
    0.85
     Reſ
    0.84
     himſelf
    0.82
     Jefus
    0.82
    Activations Density 0.002%

    No Known Activations