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. 22-GEMMASCOPE-RES-16K
    6. 5916
    Prev
    Next
    INDEX
    Explanations

    specific code formatting and syntax elements in programming languages

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

    Code, symbols, and identifiers

    np_acts-logits-general · gemini-2.0-flash

    blockList structure markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    צלחה
    -0.72
    اقرأ
    -0.66
     myſelf
    -0.65
    نتیجه
    -0.64
     zitate
    -0.60
     abbildung
    -0.60
     Wikispecies
    -0.60
    Демографія
    -0.58
     Theſe
    -0.58
    unnitel
    -0.57
    POSITIVE LOGITS
     Савезне
    0.89
     незавершена
    0.85
    Portale
    0.75
    اظ
    0.72
    पया
    0.71
    __*/
    0.68
     CreateTagHelper
    0.67
    تقاوى
    0.67
    Rüyada
    0.66
     تضيفلها
    0.65
    Activations Density 0.348%

    No Known Activations