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

    Neuronpedia

    APICircuit 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. 10126
    Prev
    Next
    INDEX
    Explanations

    references to the name "Ros" in various contexts

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

    Tokens before a number

    np_acts-logits-general · gemini-2.0-flash

    names starting with Ros or Ras

    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
     AssemblyCulture
    -0.74
    RuleContext
    -0.68
    Personendaten
    -0.67
     AspNetCore
    -0.64
    EndGlobalSection
    -0.61
    zzleHttp
    -0.59
    tonode
    -0.59
    DropColumn
    -0.56
    mallows
    -0.55
     laby
    -0.54
    POSITIVE LOGITS
     للاسماء
    0.72
    \"");
    0.61
    *}{
    0.54
    ouw
    0.52
    latimes
    0.51
    最快更新
    0.51
    #
    0.49
     {_
    0.49
     '').
    0.48
     "").
    0.47
    Activations Density 0.099%

    No Known Activations