© 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. 16135
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics that reflect quantitative measurements

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

    Numbers in parentheses

    np_acts-logits-general · gemini-2.0-flash

    two or pairs

    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
    4
    -0.71
    5
    -0.69
     five
    -0.65
     four
    -0.61
     fifth
    -0.60
     ۵
    -0.60
     fün
    -0.60
     پنج
    -0.60
     Five
    -0.58
     SIX
    -0.58
    POSITIVE LOGITS
     FetchType
    0.63
     Two
    0.63
     two
    0.63
    two
    0.62
    Two
    0.59
     дву
    0.55
    Segunda
    0.55
     deux
    0.54
     Zwe
    0.54
     tartalomajánló
    0.54
    Activations Density 0.329%

    No Known Activations