© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 5736
    Prev
    Next
    INDEX
    Explanations

    references to nuclear energy and its development in Europe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    text discussing global policy initiatives, international organizations, and collaborative efforts addressing major challenges like climate change, energy, and sustainability.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    large numbers and quantities, particularly those appearing in contexts involving data, statistics, or policy targets.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.59
     idéia
    -0.56
     iNdEx
    -0.53
    daß
    -0.49
    RegressionTest
    -0.47
     DVD
    -0.47
     biß
    -0.46
     Miß
    -0.45
     Einfluß
    -0.44
    jsonwebtoken
    -0.44
    POSITIVE LOGITS
     decarbon
    0.81
    DIGITAL
    0.60
     digitalen
    0.59
     digital
    0.57
    Digital
    0.55
     digitais
    0.55
     digitale
    0.55
    デジタル
    0.54
     numérique
    0.54
     resilience
    0.53
    Activations Density 0.156%

    No Known Activations