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. 2-GEMMASCOPE-RES-16K
    6. 15067
    Prev
    Next
    INDEX
    Explanations

    references to programming and system installation on different operating systems, particularly related to compiling and linking libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.55
    NamedQueries
    -0.54
    protoimpl
    -0.51
     intptr
    -0.51
     TextEditing
    -0.51
    ılmıştır
    -0.50
    MessageOf
    -0.47
    IsContent
    -0.47
    脚注の使い方
    -0.46
    GraphicsUnit
    -0.46
    POSITIVE LOGITS
     Jefus
    0.69
     faſt
    0.68
     Chriſt
    0.66
     computers
    0.65
     poffe
    0.63
     Reſ
    0.63
     Diſ
    0.62
     itſelf
    0.62
    detectChanges
    0.61
     himſelf
    0.61
    Activations Density 1.222%

    No Known Activations