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. 12-GEMMASCOPE-RES-16K
    6. 7943
    Prev
    Next
    INDEX
    Explanations

    references to Brazil and its political landscape

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dianteiro
    -0.79
     traseiro
    -0.74
     Soria
    -0.69
     mesmas
    -0.68
    iquest
    -0.66
     Deportes
    -0.65
     gammal
    -0.64
     nisso
    -0.64
    ocidad
    -0.64
     morrer
    -0.64
    POSITIVE LOGITS
    scriptcase
    0.91
     Brazil
    0.83
    VersionUID
    0.82
     Portugal
    0.80
     Brasil
    0.79
    Neymar
    0.76
     Brazilian
    0.75
     Braz
    0.75
    Brazilian
    0.75
    Portugal
    0.74
    Activations Density 0.290%

    No Known Activations