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. 19-GEMMASCOPE-RES-16K
    6. 2001
    Prev
    Next
    INDEX
    Explanations

    details related to nonprofit organizations and their initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -1.00
    bootstrapcdn
    -0.71
     noDo
    -0.68
    RectangleBorder
    -0.67
    BeginContext
    -0.66
     NSCoder
    -0.65
    ISupport
    -0.65
    脚注の使い方
    -0.64
    XmlAccessType
    -0.60
    
    -0.60
    POSITIVE LOGITS
     aims
    1.21
     aimed
    1.09
     aim
    0.98
     aiming
    0.94
     focuses
    0.88
     seeks
    0.85
     bertujuan
    0.85
     focused
    0.84
     focus
    0.83
    旨在
    0.81
    Activations Density 0.219%

    No Known Activations