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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-ATT-16K
    6. 6514
    Prev
    Next
    INDEX
    Explanations

    attends to the token "are" from tokens that represent ongoing actions or states

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    0:0.08
    1:0.09
    2:0.09
    3:0.15
    4:0.12
    5:0.02
    6:0.29
    7:0.12
    Negative Logits
    Демографія
    -0.28
    ↵↵
    -0.25
    ɜ
    -0.25
     organisation
    -0.24
    非常的
    -0.24
    crombie
    -0.24
    люсы
    -0.24
    Carriera
    -0.23
    を開
    -0.23
     Einf
    -0.23
    POSITIVE LOGITS
    ReusableCell
    0.50
    MLLoader
    0.48
    invokeLater
    0.42
    KommentareTeilen
    0.42
    Cyfeiriadau
    0.42
     Wiktionnaire
    0.39
     дописавши
    0.37
     AppCompatTheme
    0.36
     doPost
    0.36
    batore
    0.36
    Activations Density 0.063%

    No Known Activations