© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 8657
    Prev
    Next
    INDEX
    Explanations

    terms and references related to news and journalism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.60
     oprot
    -0.58
    AlterField
    -0.55
     réessayer
    -0.52
    Abitanti
    -0.49
    FactoryBean
    -0.49
    AccessorTable
    -0.47
    ModelAttribute
    -0.47
     מול
    -0.47
     mergeFrom
    -0.46
    POSITIVE LOGITS
     news
    3.98
    news
    3.52
    News
    3.38
     News
    3.37
     NEWS
    3.21
    NEWS
    3.00
     nieuws
    2.44
     noticias
    2.43
     noticia
    2.35
     뉴스
    2.16
    Activations Density 0.068%

    No Known Activations