© 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. 17-GEMMASCOPE-RES-16K
    6. 2047
    Prev
    Next
    INDEX
    Explanations

    mentions of attention and its various contexts in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perfección
    -0.61
    raborty
    -0.56
    bruch
    -0.55
    sy
    -0.54
    ak
    -0.53
     Kurdistan
    -0.53
     Gilman
    -0.52
    裔
    -0.52
    ad
    -0.52
    rabh
    -0.51
    POSITIVE LOGITS
     attention
    1.51
     Attention
    1.43
     ATTENTION
    1.29
    Attention
    1.27
    attention
    1.25
    ATTENTION
    1.21
     attentions
    1.09
    attenzione
    1.03
     Atención
    0.92
     aandacht
    0.89
    Activations Density 0.067%

    No Known Activations