© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5690
    Prev
    Next
    INDEX
    Explanations

    references to quantitative limits or thresholds, particularly in legal or regulatory contexts

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

    Following "the" or a number

    np_acts-logits-general · gemini-2.0-flash

    limits and thresholds

    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
    EndTag
    -0.57
     autorytatywna
    -0.56
    PerformLayout
    -0.55
     onOptions
    -0.54
    forName
    -0.52
    abestanden
    -0.52
    belongsTo
    -0.49
     "..\..\..\
    -0.49
     ReactDOM
    -0.48
    
    -0.47
    POSITIVE LOGITS
     limit
    2.13
     limits
    1.89
     Limit
    1.72
    limit
    1.68
     threshold
    1.67
     limite
    1.66
     minimum
    1.64
     Limits
    1.58
    Limit
    1.58
     límite
    1.58
    Activations Density 0.860%

    No Known Activations