© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14-GEMMASCOPE-RES-16K
    11. 14482
    Prev
    Next
    INDEX
    Explanations

    phrases related to varying approaches or perspectives on a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Thunk
    -0.58
     instalação
    -0.56
     économies
    -0.54
     instalación
    -0.50
     résidence
    -0.48
     sozinho
    -0.47
    stätte
    -0.47
     soldati
    -0.47
    Pall
    -0.46
    ux
    -0.45
    POSITIVE LOGITS
     approach
    1.18
    approach
    1.17
    Approach
    1.09
     Approach
    1.06
     APPROACH
    1.05
    approche
    0.95
     approaches
    0.93
     view
    0.92
     views
    0.88
     outlook
    0.85
    Activations Density 0.272%

    No Known Activations