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. 12-GEMMASCOPE-RES-16K
    6. 9670
    Prev
    Next
    INDEX
    Explanations

    mentions of the United Nations (UN) and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.83
     Poche
    -0.78
    styleType
    -0.77
     Ciri
    -0.75
     виправивши
    -0.74
     auffi
    -0.74
     وتسجيلات
    -0.74
     Phry
    -0.70
    enumii
    -0.69
    incen
    -0.68
    POSITIVE LOGITS
     UN
    1.25
    UN
    1.13
     Unions
    1.04
    union
    1.01
    UNION
    0.98
     unions
    0.92
     Unis
    0.91
     Union
    0.90
     UNION
    0.89
     Munro
    0.87
    Activations Density 0.131%

    No Known Activations