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. 12589
    Prev
    Next
    INDEX
    Explanations

    phrases related to electoral processes and campaign dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     ansatte
    -0.51
     voors
    -0.50
     humanidad
    -0.48
     procrastination
    -0.46
     especies
    -0.46
     australiano
    -0.45
    thebibliography
    -0.45
     permanentes
    -0.45
     bilinear
    -0.45
     Dubrovnik
    -0.44
    POSITIVE LOGITS
     ModelExpression
    0.95
     voters
    0.88
    ніципалі
    0.85
     electoral
    0.85
     voter
    0.84
     estekak
    0.81
     Voters
    0.79
     elector
    0.79
     snippetHide
    0.79
     electorate
    0.79
    Activations Density 0.317%

    No Known Activations