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. 17-GEMMASCOPE-RES-16K
    6. 7189
    Prev
    Next
    INDEX
    Explanations

    terms related to international financial institutions and their impact on developing nations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.76
    UpInside
    -0.59
     facie
    -0.57
    IBarButtonItem
    -0.57
    спубли
    -0.55
     SwiftUI
    -0.55
    ❉
    -0.52
    derry
    -0.52
     typelib
    -0.51
     ویکی‌پدی
    -0.51
    POSITIVE LOGITS
     &___
    0.75
     multilateral
    0.68
    DOCTYPE
    0.61
    missions
    0.54
    adone
    0.53
     organization
    0.52
    ($__
    0.52
    QFont
    0.52
     World
    0.51
     Welt
    0.51
    Activations Density 0.100%

    No Known Activations