© 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. 18-GEMMASCOPE-RES-16K
    11. 14931
    Prev
    Next
    INDEX
    Explanations

    numerical expressions and mathematical operations

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

    Fractions and arithmetic operations

    np_acts-logits-general · gemini-2.0-flash

    fractions and their operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.64
       
    -0.63
     dessus
    -0.60
    nocześnie
    -0.59
     surla
    -0.59
    cules
    -0.59
    Liên
    -0.58
     وتسجيلات
    -0.58
    /}{
    -0.58
     InputDecoration
    -0.57
    POSITIVE LOGITS
    InSection
    0.75
    rds
    0.62
     tră
    0.56
    astéro
    0.55
    ErrUnexpectedEOF
    0.52
    脚注の使い方
    0.51
     NSCoder
    0.51
    jsonwebtoken
    0.51
     infarction
    0.49
    程度上
    0.48
    Activations Density 0.343%

    No Known Activations