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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 102991
    Prev
    Next
    INDEX
    Explanations

    references to peace treaties and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    :+:
    -0.44
     transfieras
    -0.37
     Gotham
    -0.35
     Futura
    -0.32
     your
    -0.32
    ########.
    -0.32
    참고
    -0.32
     mask
    -0.31
     nice
    -0.30
    Car
    -0.30
    POSITIVE LOGITS
     EconPapers
    0.65
    orianCalendar
    0.62
     يتيمه
    0.61
    DrawerToggle
    0.58
     betrek
    0.57
     recrutement
    0.57
    addCriterion
    0.54
    ulongan
    0.54
    bague
    0.54
    ainville
    0.53
    Activations Density 0.022%

    No Known Activations