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. 20-GEMMASCOPE-RES-16K
    6. 2109
    Prev
    Next
    INDEX
    Explanations

    references to the World Health Organization (WHO) and related health data

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

    "Organization" or "Organisation"

    np_acts-logits-general · gemini-2.0-flash

    world health organization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adpleegd
    -0.73
    ccoli
    -0.53
     humaine
    -0.51
    SequentialGroup
    -0.51
    AlterField
    -0.51
     Endpoint
    -0.49
    didSet
    -0.48
     geho
    -0.48
    getSystemService
    -0.48
    mainAxisSize
    -0.48
    POSITIVE LOGITS
     Organization
    1.25
     organization
    1.20
     Organisation
    1.14
     organisation
    1.11
    Organization
    1.10
     ORGANIZATION
    1.09
    organization
    1.06
    Organisation
    1.03
     org
    0.97
    ORGANIZATION
    0.95
    Activations Density 0.247%

    No Known Activations