© 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. 1-GEMMASCOPE-RES-16K
    6. 3658
    Prev
    Next
    INDEX
    Explanations

    references to different types of markets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bat
    -0.54
    antd
    -0.51
    antation
    -0.49
     للاسماء
    -0.48
     Er
    -0.48
     дописавши
    -0.48
     descar
    -0.47
     saluti
    -0.47
     purchased
    -0.46
    andra
    -0.46
    POSITIVE LOGITS
     fleet
    1.05
     Fleet
    1.03
     portfolio
    0.91
     Portfolio
    0.89
    Portfolio
    0.86
     fleets
    0.83
    portfolio
    0.83
    ส
    0.83
    djangoproject
    0.82
     pinulongan
    0.82
    Activations Density 0.069%

    No Known Activations