© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14706
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss methods, processes, or approaches

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

    "the way" or "the manner"

    np_acts-logits-general · gemini-2.0-flash

    description of how something is done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    addContainerGap
    -0.39
    Ծանոթ
    -0.36
     réun
    -0.35
    #![
    -0.35
    CodeAnalysis
    -0.35
     šk
    -0.35
    MultipartFile
    -0.34
     berguna
    -0.33
     nahilalakip
    -0.33
     yardım
    -0.32
    POSITIVE LOGITS
     manner
    0.77
    manner
    0.77
    posób
    0.74
     differently
    0.67
     Manner
    0.67
     manière
    0.66
     manier
    0.65
     way
    0.65
     autorytatywna
    0.63
    styleType
    0.60
    Activations Density 0.563%

    No Known Activations