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. 6389
    Prev
    Next
    INDEX
    Explanations

    attends to the sequence's closing asterisk token from the preceding sequence's enclosing brackets

    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
    2:0.08
    3:0.12
    4:0.10
    5:0.05
    6:0.25
    7:0.18
    Negative Logits
     
    -0.25
    スカ
    -0.24
    dll
    -0.24
    േ
    -0.23
    云
    -0.23
     GmbH
    -0.23
    ास्त
    -0.23
    ed
    -0.23
    A
    -0.22
     amp
    -0.22
    POSITIVE LOGITS
    ьаж
    0.60
    GEBURTSDATUM
    0.59
    ⓧ
    0.56
    
    0.55
    +#+#
    0.55
     Roskov
    0.54
    SourceChecksum
    0.52
    Manbalar
    0.51
     ویکی‌پدی
    0.51
     '\\;'
    0.51
    Activations Density 1.275%

    No Known Activations