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. 20-GEMMASCOPE-RES-16K
    6. 15595
    Prev
    Next
    INDEX
    Explanations

    references to collections and threading in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    C# namespace and library imports

    np_acts-logits-general · gemini-2.0-flash

    .NET collections, threading, and web

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     @"/
    -0.72
     ligiloj
    -0.70
    stolic
    -0.68
    pośred
    -0.65
     duquel
    -0.59
     revés
    -0.58
    waard
    -0.58
     espirituales
    -0.55
     réfugi
    -0.55
     समीक्षाओं
    -0.54
    POSITIVE LOGITS
    Collections
    1.06
     AssemblyCulture
    0.74
     Collections
    0.69
    脚注の使い方
    0.65
     collections
    0.59
    AndEndTag
    0.58
     considérons
    0.57
    AntiForgeryToken
    0.56
    SpringBootTest
    0.55
    ABBRE
    0.55
    Activations Density 0.012%

    No Known Activations