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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 11995
    Prev
    Next
    INDEX
    Explanations

    references to Boston and its related institutions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.94
    zsche
    -0.90
     Schmitz
    -0.77
    WindowConstants
    -0.77
     Fairchild
    -0.75
     Transvaal
    -0.73
     متعلقه
    -0.73
     Lưu
    -0.70
    AttributeSet
    -0.70
    ніципалі
    -0.70
    POSITIVE LOGITS
     Boston
    2.58
    Boston
    2.35
     BOSTON
    1.98
    BOSTON
    1.89
     Massachusetts
    1.89
     boston
    1.85
    boston
    1.78
    Massachusetts
    1.71
     Celtics
    1.37
     MASSACHUSETTS
    1.22
    Activations Density 0.169%

    No Known Activations