© 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. 8-GEMMASCOPE-RES-16K
    6. 13411
    Prev
    Next
    INDEX
    Explanations

    references to mathematical variables and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    贷款
    -0.47
     gereken
    -0.44
    ImageIcon
    -0.44
     Völker
    -0.44
    ESSION
    -0.43
     gạo
    -0.43
     proced
    -0.43
    ائية
    -0.43
     high
    -0.42
     ioutil
    -0.42
    POSITIVE LOGITS
    +#+
    0.92
    Abitanti
    0.81
    PerformLayout
    0.80
    PreferredItem
    0.79
    tangentMode
    0.79
    aarrggbb
    0.77
     AssemblyCulture
    0.75
     <<<<<<<<<<<<<<
    0.73
    transQ
    0.72
    eleste
    0.72
    Activations Density 0.769%

    No Known Activations