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. 13-GEMMASCOPE-RES-16K
    6. 15876
    Prev
    Next
    INDEX
    Explanations

    references to countries and their related contexts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chartres
    -0.83
     Berlín
    -0.75
     Milán
    -0.74
     serr
    -0.73
     Ripper
    -0.66
     frontale
    -0.66
     FEES
    -0.65
     Parigi
    -0.64
     Asparagus
    -0.63
     stole
    -0.62
    POSITIVE LOGITS
     countries
    1.30
     country
    1.24
     Country
    1.23
     Countries
    1.21
     COUNTRY
    1.19
    countries
    1.18
    Countries
    1.14
    COUNTRY
    1.05
    country
    1.03
    Country
    1.01
    Activations Density 0.040%

    No Known Activations