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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 12408
    Prev
    Next
    INDEX
    Explanations

    references to India and its societal aspects, particularly relating to work and holidays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    tagHelperRunner
    -0.61
     distanciation
    -0.55
    hysema
    -0.51
    xchange
    -0.50
     Passing
    -0.48
    навли
    -0.48
    стол
    -0.47
     SCOPE
    -0.47
    GeneratedValue
    -0.47
    DockStyle
    -0.46
    POSITIVE LOGITS
     rear
    1.78
     back
    1.71
    rear
    1.49
     backside
    1.47
     belakang
    1.46
     hinten
    1.46
     front
    1.43
    back
    1.40
     backend
    1.39
     atrás
    1.35
    Activations Density 0.300%

    No Known Activations