© 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. 9-GEMMASCOPE-RES-16K
    6. 8788
    Prev
    Next
    INDEX
    Explanations

    elements related to phone books and their structural components typically found in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.46
    RunAsync
    -0.45
     gear
    -0.43
    نيف
    -0.42
    gear
    -0.41
    imai
    -0.39
     chistes
    -0.39
     counted
    -0.39
    dispatch
    -0.39
     counter
    -0.38
    POSITIVE LOGITS
     OFDb
    1.02
     ujednoznacz
    0.97
     kasarigan
    0.90
     leetcode
    0.81
    setupUi
    0.79
     EconPapers
    0.77
    leetcode
    0.77
    etCode
    0.73
     disambiguazione
    0.72
     Italijani
    0.72
    Activations Density 0.094%

    No Known Activations