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. 7-GEMMASCOPE-RES-16K
    6. 9505
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "union" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ignacio
    -0.85
    paramref
    -0.83
    Bav
    -0.83
    +#+#
    -0.82
    enumi
    -0.78
     Dord
    -0.77
     Akade
    -0.75
     Palin
    -0.74
     Norwe
    -0.73
    innoc
    -0.73
    POSITIVE LOGITS
     union
    2.00
     Union
    1.89
    union
    1.88
    UNION
    1.87
     UNION
    1.87
     unions
    1.73
    Union
    1.71
     Unions
    1.64
     unión
    1.14
     Unión
    0.96
    Activations Density 0.056%

    No Known Activations