Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6720
    Prev
    Next
    INDEX
    Explanations

    references to locations, specifically places named "New" followed by geographical identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of geographic locations or entities related to New Jersey and its surroundings

    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
     suivante
    -0.61
     africano
    -0.60
     privados
    -0.60
    feest
    -0.57
     śmierci
    -0.57
     ambientale
    -0.57
     Warszawie
    -0.57
    کنون
    -0.57
     Guevara
    -0.56
    ViewFeatures
    -0.56
    POSITIVE LOGITS
    بوابة
    0.80
    󠁢
    0.79
     Efq
    0.74
    
    0.74
     South
    0.72
    NEX
    0.69
     North
    0.67
    ſelves
    0.66
     Lel
    0.66
    ########.
    0.66
    Activations Density 0.364%

    No Known Activations