© 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. 10-GEMMASCOPE-RES-16K
    6. 6492
    Prev
    Next
    INDEX
    Explanations

    terms related to nanotechnology and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الإنجليزية
    -1.18
     Petron
    -0.95
     Buxton
    -0.83
     Lugo
    -0.79
     Danilo
    -0.79
     XLR
    -0.78
    rostis
    -0.78
     Rossini
    -0.77
     Să
    -0.74
     Nema
    -0.74
    POSITIVE LOGITS
    ValueStyle
    1.00
    +#+#
    0.94
     cust
    0.82
    Christy
    0.81
    thanol
    0.80
     Mili
    0.80
    ❹
    0.80
     Rink
    0.77
     Christy
    0.77
     PREL
    0.75
    Activations Density 0.815%

    No Known Activations