© 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. 16289
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting in the text

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

    Tokens preceding "*et al*" or ">"

    np_acts-logits-general · gemini-2.0-flash

    `CommandType` definition parameters

    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
      
    -0.78
    <strong>
    -0.72
    <b>
    -0.69
     CreateTagHelper
    -0.68
    <i>
    -0.66
    ίας
    -0.60
    <h6>
    -0.60
    <code>
    -0.58
    <em>
    -0.55
       
    -0.55
    POSITIVE LOGITS
     GenerationType
    0.75
    EnableWeb
    0.70
    íslu
    0.60
     Thra
    0.58
     själva
    0.58
    ტერ
    0.57
     clearColor
    0.56
     ogóle
    0.55
     Anſ
    0.54
     QWidget
    0.54
    Activations Density 0.185%

    No Known Activations