Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 12363
    Prev
    Next
    INDEX
    Explanations

    references to attention and its various contexts or impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vesicle
    -0.64
     Rodgers
    -0.64
    raborty
    -0.63
    dip
    -0.63
     Roos
    -0.63
     Lehman
    -0.63
    谷川
    -0.62
    camore
    -0.62
     McBride
    -0.62
     Gefühle
    -0.61
    POSITIVE LOGITS
     attention
    2.03
     Attention
    1.83
     ATTENTION
    1.75
    attention
    1.69
    Attention
    1.66
     attentions
    1.51
    ATTENTION
    1.48
    attenzione
    1.23
     Atención
    1.20
     aten
    1.12
    Activations Density 0.050%

    No Known Activations