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. 11-GEMMASCOPE-RES-16K
    6. 13918
    Prev
    Next
    INDEX
    Explanations

    references to the sea and related water bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.00
     themſelves
    -0.95
     himſelf
    -0.89
    )";
    
    -0.83
     propOrder
    -0.80
     Bulbs
    -0.80
    )");
    
    -0.79
     Kamu
    -0.78
     purpoſe
    -0.78
     Monfieur
    -0.77
    POSITIVE LOGITS
     Sea
    1.29
     SEA
    1.26
    Sea
    1.18
     sea
    1.17
    sea
    1.02
    SEA
    1.00
     seaborn
    0.99
    ea
    0.88
     Carney
    0.85
     Rea
    0.83
    Activations Density 0.056%

    No Known Activations