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. 25-GEMMASCOPE-RES-16K
    6. 5822
    Prev
    Next
    INDEX
    Explanations

    references to historical events and periods, particularly relating to World War II and its aftermath

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.74
    SequentialGroup
    -0.70
    greja
    -0.69
     AttributeSet
    -0.66
    AddTagHelper
    -0.64
     Sélectionnez
    -0.62
     Wikimedijinoj
    -0.60
    interopRequire
    -0.59
    TagHelpers
    -0.59
    حياته
    -0.58
    POSITIVE LOGITS
     World
    1.56
    World
    1.27
     WWII
    1.21
     WW
    1.07
     WWI
    1.05
     WORLD
    0.98
    WORLD
    0.91
    WW
    0.85
     ww
    0.82
    world
    0.73
    Activations Density 0.473%

    No Known Activations