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. 403
    Prev
    Next
    INDEX
    Explanations

    sequences of characters typically used in programming code

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

    instances of the word "char" in programming contexts.

    oai_token-act-pair · gpt-4oTriggered by @timna
    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
     ?>/
    -0.87
     Tutu
    -0.87
    🙃
    -0.86
     Oppen
    -0.86
     Goliath
    -0.86
     Romain
    -0.86
     Multip
    -0.85
     Spisak
    -0.84
    moiselle
    -0.84
     Enoch
    -0.83
    POSITIVE LOGITS
     Char
    1.54
     char
    1.51
     CHAR
    1.50
    CHAR
    1.46
    Char
    1.43
    char
    1.31
     chars
    1.29
     Schar
    1.22
     Charlene
    1.16
     charts
    1.14
    Activations Density 0.084%

    No Known Activations