© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8729
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to programming and database configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estimés
    -0.75
    webElementXpaths
    -0.67
     Shakspeare
    -0.65
     Siti
    -0.63
     Administrativna
    -0.62
     Crosby
    -0.62
     Albu
    -0.61
     Shaksp
    -0.60
     Borne
    -0.57
    Рисунок
    -0.56
    POSITIVE LOGITS
    UTF
    0.66
    fin
    0.64
     arg
    0.64
    Collegamenti
    0.62
    berry
    0.61
    async
    0.60
     dele
    0.60
     Fin
    0.59
    杠
    0.59
    DoubleQuotes
    0.58
    Activations Density 2.817%

    No Known Activations