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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6097
    Prev
    Next
    INDEX
    Explanations

    references to the World Health Organization (WHO) and its classifications or predictions related to public health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    World Health Organization

    np_acts-logits-general · gemini-2.0-flash

    World Health Organization and international organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    impianto
    -0.28
    Biographie
    -0.28
     plein
    -0.27
    View
    -0.26
     advent
    -0.26
     zach
    -0.26
     CAMP
    -0.25
     fer
    -0.25
     Raymond
    -0.25
     e
    -0.25
    POSITIVE LOGITS
     WHO
    0.88
     Unesco
    0.85
    WHO
    0.84
     UNESCO
    0.83
    UNESCO
    0.80
     FAO
    0.76
    setupUi
    0.73
     ILO
    0.73
     OECD
    0.69
     UNEP
    0.67
    Activations Density 0.325%

    No Known Activations