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. 22451
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting in code or technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    MessageTagHelper
    -0.53
     AssemblyVersion
    -0.53
    MigrationBuilder
    -0.47
     ELECTRON
    -0.47
     CONSERV
    -0.45
    WithFormat
    -0.43
    menea
    -0.42
    gotoxy
    -0.41
     betweenstory
    -0.41
     Warner
    -0.41
    POSITIVE LOGITS
    Twig
    0.84
     CanadaChoose
    0.70
    fjspx
    0.63
     चीज़ों
    0.61
    Décès
    0.59
    SourceChecksum
    0.51
     Twig
    0.51
     '\\;'
    0.50
    Kaynakça
    0.48
     Commencez
    0.48
    Activations Density 0.000%

    No Known Activations