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. 53775
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting related to numerical data

    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
    IndentedString
    -0.38
    神
    -0.38
     مس
    -0.35
    MethodManager
    -0.35
    endregion
    -0.34
     fin
    -0.33
    دانشنامهٔ
    -0.33
    内
    -0.32
     Ebers
    -0.32
     ing
    -0.32
    POSITIVE LOGITS
    PerformLayout
    0.68
     snippetHide
    0.68
    afficheront
    0.67
    ſelves
    0.66
     poffible
    0.64
    ſelf
    0.59
     ddelwed
    0.58
     Taktlose
    0.58
    +#+#
    0.57
     leaſt
    0.56
    Activations Density 0.078%

    No Known Activations