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. 103180
    Prev
    Next
    INDEX
    Explanations

    preprocessor directives in code

    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
    featureID
    -0.66
     мәкал
    -0.54
    Rüyada
    -0.51
     JpaRepository
    -0.48
    ->___
    -0.46
    IActionResult
    -0.45
     direkten
    -0.45
     teorías
    -0.45
     musí
    -0.44
    transQ
    -0.43
    POSITIVE LOGITS
    arXiv
    0.68
     nahilalakip
    0.64
    findpost
    0.49
    发表于
    0.46
    httphttps
    0.46
     EconPapers
    0.45
    Datuak
    0.44
     Audiodateien
    0.42
     ſeveral
    0.42
    Viited
    0.42
    Activations Density 0.000%

    No Known Activations