© 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. 15-GEMMASCOPE-RES-16K
    6. 771
    Prev
    Next
    INDEX
    Explanations

    dates and numbers, particularly in the context of legal or formal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Arco
    -0.81
     Efq
    -0.80
    parsedMessage
    -0.80
     tartalomajánló
    -0.75
    AsUp
    -0.75
    izontal
    -0.75
    monials
    -0.72
    Personendaten
    -0.71
    InputBorder
    -0.71
     Zij
    -0.71
    POSITIVE LOGITS
     bry
    0.54
     seed
    0.54
    ftagPool
    0.54
     Seed
    0.53
    +:+
    0.52
    वरण
    0.51
    <0xBF>
    0.50
    seed
    0.49
     Duncan
    0.49
    fz
    0.48
    Activations Density 0.578%

    No Known Activations