© 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. 34-GEMMASCOPE-RES-16K
    11. 10878
    Prev
    Next
    INDEX
    Explanations

    formal expressions of obligation or duty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moniker
    -0.70
     transitioning
    -0.63
     critters
    -0.62
     aforementioned
    -0.59
     attendees
    -0.59
     proactively
    -0.58
     anytime
    -0.57
     Drittan
    -0.56
     impactful
    -0.56
     upcoming
    -0.56
    POSITIVE LOGITS
    SequentialGroup
    0.62
     läßt
    0.55
    UrlResolution
    0.54
    ThroughAttribute
    0.53
     Miß
    0.52
     biß
    0.50
    請繼續往下閱讀
    0.48
     skall
    0.48
    そういう
    0.47
    ้งาน
    0.47
    Activations Density 1.434%

    No Known Activations