© 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. 25-GEMMASCOPE-RES-16K
    11. 14981
    Prev
    Next
    INDEX
    Explanations

    phrases related to maintaining standards, consistency, or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anſ
    -0.89
     Houſe
    -0.77
    ésultats
    -0.75
     $_(
    -0.75
    MessageOf
    -0.74
     ſche
    -0.73
     Jefus
    -0.72
     Reſ
    -0.72
     AppModule
    -0.70
     fubject
    -0.70
    POSITIVE LOGITS
    maintain
    0.93
     Maintain
    0.92
    Maintain
    0.91
     maintain
    0.84
     maintains
    0.82
     maintained
    0.82
    maintenance
    0.82
    maintained
    0.78
     maintaining
    0.77
     maintenir
    0.76
    Activations Density 0.154%

    No Known Activations