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. 693
    Prev
    Next
    INDEX
    Explanations

    references to companies and specific products associated with genetics and finance

    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
    GEBURTSDATUM
    -0.56
     precedentes
    -0.46
    ftagPool
    -0.45
     dibujado
    -0.44
     EClass
    -0.43
    Démographie
    -0.43
    WebServlet
    -0.43
    ρέπει
    -0.42
    WebElementEntity
    -0.41
    complexContent
    -0.41
    POSITIVE LOGITS
     company
    0.72
     gynhyrchwyd
    0.69
     brand
    0.64
     Company
    0.63
     proprietary
    0.61
     website
    0.59
    TypedDataSet
    0.58
     corporation
    0.57
     oprot
    0.54
    Ottimo
    0.54
    Activations Density 0.584%

    No Known Activations