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. 1931
    Prev
    Next
    INDEX
    Explanations

    instances of the word "char" or related variations in programming contexts

    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
     Enoch
    -0.85
     PX
    -0.84
    óbal
    -0.81
     Multip
    -0.79
    venido
    -0.77
     Oppen
    -0.76
     Petrov
    -0.75
    typeparam
    -0.74
     Goliath
    -0.74
    LikeLike
    -0.73
    POSITIVE LOGITS
     Char
    1.32
     CHAR
    1.29
     charts
    1.27
     char
    1.22
    CHAR
    1.21
     Charts
    1.19
    Char
    1.18
     Charlene
    1.18
     chars
    1.14
     chart
    1.07
    Activations Density 0.067%

    No Known Activations