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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 35565
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "world" in various contexts

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

    World War

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    TabIndex
    -0.47
    atalytic
    -0.46
     Hackney
    -0.44
     Rinse
    -0.44
     either
    -0.41
     Lacy
    -0.41
    Rinse
    -0.40
    taminophen
    -0.40
    jména
    -0.39
     Hitch
    -0.38
    POSITIVE LOGITS
    World
    1.36
     World
    1.29
    world
    1.24
     world
    1.21
     WORLD
    1.20
    WORLD
    1.18
    getWorld
    1.00
    orld
    0.96
     worlds
    0.95
     Worlds
    0.91
    Activations Density 0.027%

    No Known Activations