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. 114493
    Prev
    Next
    INDEX
    Explanations

    names and titles related to individuals in sports and politics

    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
     MainAxisSize
    -0.66
     ſur
    -0.64
    portál
    -0.60
     queſta
    -0.60
     Jefus
    -0.60
     faſt
    -0.60
     itſelf
    -0.59
    :✨
    -0.59
     ujednoznacz
    -0.59
     tranſ
    -0.57
    POSITIVE LOGITS
     Jamaica
    0.65
     Jamaican
    0.60
     Barbados
    0.58
     Caribbean
    0.56
    Jamaica
    0.52
     Tobago
    0.51
     persons
    0.47
     Trinidad
    0.47
    Barbados
    0.46
     Guyana
    0.45
    Activations Density 0.046%

    No Known Activations