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. 21-GEMMASCOPE-RES-16K
    6. 931
    Prev
    Next
    INDEX
    Explanations

    brands and models of electric vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.73
     للمعارف
    -0.62
    PreferredItem
    -0.61
     CWE
    -0.60
     fuel
    -0.55
     Adhe
    -0.53
     Fuel
    -0.53
     hybride
    -0.51
     hybrid
    -0.51
    Fuel
    -0.51
    POSITIVE LOGITS
     Tesla
    1.05
    Tesla
    0.94
     Model
    0.84
     tesla
    0.83
     Elon
    0.79
    AccessorTable
    0.74
    Model
    0.71
    tesla
    0.70
    特斯拉
    0.70
     SpaceX
    0.69
    Activations Density 0.112%

    No Known Activations