© 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. 22-GEMMASCOPE-RES-16K
    11. 14046
    Prev
    Next
    INDEX
    Explanations

    phrases related to the action of generating or producing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nodeValue
    -0.47
     integridad
    -0.45
    topRight
    -0.44
     obligación
    -0.44
     äls
    -0.43
     pestaña
    -0.43
     onClose
    -0.42
     beſt
    -0.42
     Atlántico
    -0.42
    🛑
    -0.42
    POSITIVE LOGITS
     generator
    0.96
    generate
    0.95
     generate
    0.93
     Generators
    0.90
     Generator
    0.88
     generators
    0.88
     Generate
    0.87
    generation
    0.85
     Generated
    0.84
     generated
    0.83
    Activations Density 0.196%

    No Known Activations