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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 4884
    Prev
    Next
    INDEX
    Explanations

    code snippets and examples related to programming

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

    Transitional phrases that introduce or reference supplementary content such as code examples, links, media, or additional information.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    GEBURTSDATUM
    -0.77
     pinulongan
    -0.54
     Infór
    -0.51
    EndGlobalSection
    -0.50
     Políticas
    -0.49
     automatiques
    -0.48
    withIdentifier
    -0.48
    Viited
    -0.48
    تقاوى
    -0.47
    новниш
    -0.47
    POSITIVE LOGITS
    tagext
    0.45
    נטרנט
    0.40
    पया
    0.34
     propOrder
    0.33
     CreateTagHelper
    0.33
    Diweddarwch
    0.33
    HasMaxLength
    0.31
     Dried
    0.30
    VisualStyle
    0.30
    exact
    0.30
    Activations Density 0.049%

    No Known Activations