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. 21-GEMMASCOPE-RES-16K
    6. 882
    Prev
    Next
    INDEX
    Explanations

    references to table etiquette and the proper use of utensils

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Patch
    -0.57
     patch
    -0.54
     shingles
    -0.53
    roides
    -0.52
     huden
    -0.52
     souverain
    -0.52
    Patches
    -0.51
     patches
    -0.51
    patch
    -0.50
     PATCH
    -0.49
    POSITIVE LOGITS
     glassware
    1.07
     cutlery
    1.06
     tableware
    1.03
     cups
    1.01
     spoon
    0.99
     glass
    0.99
     utensils
    0.99
     cup
    0.98
     silverware
    0.96
     plates
    0.94
    Activations Density 0.158%

    No Known Activations