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. 5998
    Prev
    Next
    INDEX
    Explanations

    instances of the word "compare" or its derivatives

    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
    NegativeButton
    -0.76
     Rosenberg
    -0.67
    entgen
    -0.66
     Man
    -0.62
     Henn
    -0.60
    entu
    -0.60
    enegger
    -0.59
    ffman
    -0.59
    jména
    -0.57
     aguja
    -0.56
    POSITIVE LOGITS
     Comparisons
    1.47
     comparisons
    1.43
     comparison
    1.42
     compar
    1.34
     compares
    1.34
     compared
    1.32
     Compar
    1.31
     Comparing
    1.31
     Comparison
    1.30
     Compare
    1.28
    Activations Density 0.145%

    No Known Activations