© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13350
    Prev
    Next
    INDEX
    Explanations

    elements related to revision control and database management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.70
     चीज़ों
    -0.56
    
    -0.50
    LookAnd
    -0.49
    AddHtmlAttribute
    -0.48
    ollectionView
    -0.48
    httphttps
    -0.47
    endphp
    -0.46
    BagLayout
    -0.46
    はじめに
    -0.45
    POSITIVE LOGITS
    IsContent
    0.43
     infrared
    0.42
    férences
    0.41
    UrlEncoded
    0.40
    nlm
    0.38
    llbracket
    0.38
    entile
    0.37
    ASO
    0.37
     preced
    0.36
    ibos
    0.36
    Activations Density 1.380%

    No Known Activations