Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14543
    Prev
    Next
    INDEX
    Explanations

    phrases reflecting personal aspirations and challenges

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

    Preceding the word "life"

    np_acts-logits-general · gemini-2.0-flash

    life and lives

    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
    っこう
    -0.50
    }-${
    -0.49
    SpringBootTest
    -0.49
     ModelExpression
    -0.48
     Dür
    -0.47
    UnsafeEnabled
    -0.46
     sunburn
    -0.45
    AddHtmlAttribute
    -0.45
     Magen
    -0.45
    '])){
    
    -0.45
    POSITIVE LOGITS
     life
    2.89
    life
    2.39
     Life
    2.25
    Life
    2.21
     LIFE
    2.20
    LIFE
    2.11
     lives
    2.03
     жизни
    1.99
     vida
    1.94
     Leben
    1.83
    Activations Density 0.257%

    No Known Activations