© 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. 2-GEMMASCOPE-RES-16K
    6. 4161
    Prev
    Next
    INDEX
    Explanations

    technical terms and names related to telecommunications and technology markets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pend
    -0.77
    Boas
    -0.72
     
    -0.66
     متعلقه
    -0.66
     Kön
    -0.64
    ReusableCell
    -0.64
    Snack
    -0.63
    czas
    -0.62
    вку
    -0.61
    Guido
    -0.61
    POSITIVE LOGITS
    abestanden
    0.79
     Fayetteville
    0.77
    Sop
    0.73
     Petal
    0.70
     Burch
    0.69
    Floral
    0.69
     Lenz
    0.69
     Floral
    0.68
    %");
    0.68
    例文帳に追加
    0.67
    Activations Density 7.293%

    No Known Activations