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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 128
    Prev
    Next
    INDEX
    Explanations

    attends to tokens related to "nan" from adjacent tokens related to various forms or categories

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.01
    2:0.02
    3:0.01
    4:0.68
    5:0.15
    6:0.01
    7:0.03
    Negative Logits
    ंदीखरीदारी
    -0.57
    ValueGeneration
    -0.54
    reportWebVitals
    -0.54
    noinspection
    -0.52
     дописавши
    -0.51
    enderror
    -0.49
     arşivlendi
    -0.48
    onAttach
    -0.47
     ویکی‌پدیای
    -0.47
     Audiodateien
    -0.47
    POSITIVE LOGITS
    |>
    0.28
     úč
    0.27
     !=
    0.27
     ?
    0.27
     ago
    0.26
     
    0.26
    SOUNDBITE
    0.26
    vd
    0.26
      
    0.26
    ekš
    0.25
    Activations Density 5.275%

    No Known Activations