© 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. 0-GEMMASCOPE-RES-16K
    11. 6860
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preference or superiority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     preocupación
    -0.47
     deterioro
    -0.46
     šķ
    -0.43
     preocupaciones
    -0.42
    étend
    -0.41
    <h2>
    -0.40
     męska
    -0.40
    Referanser
    -0.39
     Wochenende
    -0.38
     ciertamente
    -0.38
    POSITIVE LOGITS
     favor
    0.81
     Favor
    0.80
    Favor
    0.73
     favors
    0.72
    favor
    0.70
     favour
    0.69
     favours
    0.65
     favorable
    0.63
     favourable
    0.62
     pm
    0.57
    Activations Density 0.422%

    No Known Activations