© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 880
    Prev
    Next
    INDEX
    Explanations

    phrases indicating features or specifications of products and experiments

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

    Code, experiments, and technical documentation

    np_acts-logits-general · gemini-2.0-flash

    technical documentation sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mediately
    -0.45
     Stationary
    -0.42
     stationary
    -0.40
     Invasion
    -0.40
     estekak
    -0.40
     umbilical
    -0.39
     benches
    -0.39
    ulit
    -0.38
    urbation
    -0.38
    理石
    -0.38
    POSITIVE LOGITS
    :✨
    0.74
    webElementXpaths
    0.59
    Personendaten
    0.58
    ViewFeatures
    0.57
    parsedMessage
    0.50
     récon
    0.50
     pinulongan
    0.47
     DbSet
    0.45
     disambiguazione
    0.45
    styleType
    0.45
    Activations Density 0.012%

    No Known Activations