© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1953
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize reasonableness or logical assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.85
     Agassi
    -0.82
    BeginContext
    -0.69
    isContained
    -0.68
    CodeAttribute
    -0.68
     victims
    -0.67
    Externí
    -0.67
    Collegamenti
    -0.66
    HasColumnName
    -0.66
     Transparency
    -0.65
    POSITIVE LOGITS
     razonable
    1.06
     reasonable
    0.97
     raisonnable
    0.97
     sensible
    0.91
     reaſon
    0.90
     rational
    0.88
     REASON
    0.86
    Reasonable
    0.84
     Reason
    0.82
     sane
    0.81
    Activations Density 0.255%

    No Known Activations