Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 11655
    Prev
    Next
    INDEX
    Explanations

    titles and notable phrases from creative works, specifically in literature and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.70
    تقاوى
    -0.52
    ंदीखरीदारी
    -0.49
    曖昧さ回避
    -0.46
    cookieParser
    -0.46
    -------------</
    -0.44
     cuillère
    -0.44
    Insee
    -0.43
    mehr
    -0.43
     ویکی‌پدیای
    -0.42
    POSITIVE LOGITS
    最快更新
    0.83
     Efq
    0.74
     titulada
    0.74
     entitled
    0.71
    ✨:
    0.70
     titled
    0.70
     titulado
    0.68
    ]='\
    0.66
     berjudul
    0.65
     untitled
    0.64
    Activations Density 0.134%

    No Known Activations