© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 5345
    Prev
    Next
    INDEX
    Explanations

    references to the World Health Organization (WHO) and related organizations or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ἰ
    -0.56
     nele
    -0.52
     ostavi
    -0.51
    Particular
    -0.50
    Duc
    -0.49
     ویکی‌پدی
    -0.49
    UnusedPrivate
    -0.49
     Baus
    -0.48
    èr
    -0.48
    hadur
    -0.48
    POSITIVE LOGITS
     WHO
    0.79
     official
    0.76
    WHO
    0.73
    ollectionView
    0.68
    textTheme
    0.65
    #+#
    0.65
     FAO
    0.65
     UNESCO
    0.65
    談社
    0.64
    Économie
    0.61
    Activations Density 0.307%

    No Known Activations