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. 12073
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters, particularly in contexts that relate to functions or commands

    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
     EconPapers
    -0.85
     myſelf
    -0.80
    expandindo
    -0.76
     itſelf
    -0.76
     AppColors
    -0.76
    tagHelperRunner
    -0.72
     edelstahl
    -0.70
     allAfrica
    -0.70
    NSYLVANIA
    -0.69
     purpoſe
    -0.69
    POSITIVE LOGITS
     (;;
    0.51
    awtextra
    0.47
    нительно
    0.45
     AssemblyCulture
    0.45
     it
    0.44
     are
    0.43
    sidemargin
    0.43
     poco
    0.42
     kont
    0.42
    ↵
    0.42
    Activations Density 0.147%

    No Known Activations