© 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. 2-GEMMASCOPE-RES-16K
    11. 4101
    Prev
    Next
    INDEX
    Explanations

    terms related to sudden changes or disruptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     loop
    -0.80
     propOrder
    -0.77
    loop
    -0.76
     loops
    -0.65
     Schwangerschaft
    -0.64
    igshid
    -0.63
     stationnement
    -0.62
    höhung
    -0.62
     artesanales
    -0.59
     esenciales
    -0.58
    POSITIVE LOGITS
     lung
    1.17
     Lung
    1.05
     synchron
    1.02
     Synchron
    1.01
     lungs
    0.97
     synchronization
    0.90
    Lung
    0.89
    Sync
    0.87
     synchronize
    0.86
     synch
    0.86
    Activations Density 0.045%

    No Known Activations