© 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. 22-GEMMASCOPE-RES-16K
    11. 13451
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting symbols within sentences

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

    Method calls with no arguments

    np_acts-logits-general · gemini-2.0-flash

    method calls after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.49
    ёл
    -0.41
     llamada
    -0.41
    ArrayOf
    -0.40
     sırasında
    -0.39
    꼴
    -0.38
     schop
    -0.38
      
    -0.38
     occhi
    -0.38
     csin
    -0.37
    POSITIVE LOGITS
    
    0.88
     HasFactory
    0.87
    IntoConstraints
    0.81
     Paglinawan
    0.78
    ///</
    0.77
    tanleria
    0.76
    omeness
    0.75
    tvguidetime
    0.74
    webElementXpaths
    0.73
    IsContent
    0.73
    Activations Density 0.154%

    No Known Activations