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. 9-GEMMASCOPE-RES-16K
    6. 7823
    Prev
    Next
    INDEX
    Explanations

    references to external links or archived content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -1.08
     ویکی‌پدی
    -1.01
     GetEnumerator
    -0.98
     Roskov
    -0.98
     الرياضيه
    -0.94
     Paglinawan
    -0.93
     endwhile
    -0.92
    ItemBackground
    -0.92
    日閲覧
    -0.86
    Hozzáférés
    -0.86
    POSITIVE LOGITS
     محفوظة
    1.27
     оригіналу
    1.21
    istoitu
    0.91
     Архивировано
    0.76
    原始内容存档于
    0.72
     trữ
    0.72
    Архівовано
    0.67
     копия
    0.64
     оригинала
    0.62
     مؤرشف
    0.62
    Activations Density 0.048%

    No Known Activations