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. 11-GEMMASCOPE-RES-16K
    6. 5881
    Prev
    Next
    INDEX
    Explanations

    points and criteria related to evidence or legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.88
    :✨
    -0.86
    клопе
    -0.83
    RenderAtEndOf
    -0.82
     चीज़ों
    -0.81
     للمعارف
    -0.79
    addCriterion
    -0.77
    fromnode
    -0.76
    Personendaten
    -0.75
    المناصب
    -0.73
    POSITIVE LOGITS
    Boxscore
    0.43
     Presse
    0.42
    Champagne
    0.39
     Champagne
    0.39
    berley
    0.39
    értelmű
    0.39
    czuk
    0.38
    arez
    0.38
    ีย
    0.37
    ifornie
    0.37
    Activations Density 1.063%

    No Known Activations