© 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. 10-GEMMASCOPE-RES-16K
    11. 11763
    Prev
    Next
    INDEX
    Explanations

    phrases and terms that denote alternative meanings or definitions, often in a contrived or humorous context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Verhält
    -0.34
     cuad
    -0.33
    เลย
    -0.32
     rides
    -0.32
     juist
    -0.29
     ocio
    -0.29
    ⓧ
    -0.28
     gewiß
    -0.28
     waard
    -0.28
     olas
    -0.28
    POSITIVE LOGITS
     propOrder
    0.75
     meaning
    0.71
    meaning
    0.68
    Meaning
    0.67
     Meaning
    0.66
     equivalently
    0.62
     meanings
    0.61
     synonyms
    0.60
     wikipagina
    0.60
     significato
    0.60
    Activations Density 0.552%

    No Known Activations