© 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. 15-GEMMASCOPE-RES-16K
    11. 1048
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to high-stakes situations or the significance of legal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.94
    XmlAccessorType
    -0.60
     noten
    -0.59
     дописавши
    -0.52
     attiva
    -0.52
    styleType
    -0.51
    EndInit
    -0.51
    artal
    -0.50
    rady
    -0.46
    Distribución
    -0.46
    POSITIVE LOGITS
     stakes
    1.00
     enjeux
    0.79
    stakes
    0.64
     potentially
    0.64
     Stakes
    0.64
     risking
    0.58
    potentially
    0.58
     stake
    0.57
     risked
    0.56
     crucial
    0.55
    Activations Density 0.318%

    No Known Activations