© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 13301
    Prev
    Next
    INDEX
    Explanations

    HTML and XML elements and their attributes

    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
     Infórmanos
    -0.69
     jsPsych
    -0.52
    出版年
    -0.42
     betweenstory
    -0.42
    ----</
    -0.39
    WithMany
    -0.38
    发表于
    -0.38
     pinulongan
    -0.37
     Italij
    -0.36
    zeß
    -0.36
    POSITIVE LOGITS
     resourceCulture
    0.61
    adaptiveStyles
    0.59
     propOrder
    0.57
    haikusbot
    0.56
    SharedCtor
    0.56
    ynb
    0.54
    setObjectName
    0.53
    migrationBuilder
    0.53
     ModelExpression
    0.50
    GRANTED
    0.49
    Activations Density 1.369%

    No Known Activations