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. 6476
    Prev
    Next
    INDEX
    Explanations

    attends to conjunctions or punctuation tokens from preceding tokens that indicate a pause or transition

    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
    0:0.09
    1:0.10
    2:0.11
    3:0.16
    4:0.14
    5:0.04
    6:0.19
    7:0.13
    Negative Logits
    ksesta
    -0.29
    UVWXYZ
    -0.28
     nevo
    -0.25
    richTextPanel
    -0.25
     ladd
    -0.22
    SuppressMessage
    -0.22
     accedi
    -0.22
    AccessorTable
    -0.22
    ksessa
    -0.22
    XtraGrid
    -0.21
    POSITIVE LOGITS
    principalTable
    0.38
    存于互联网档案馆
    0.35
     tartalomajánló
    0.35
    )))),
    0.34
     ſche
    0.34
     myſelf
    0.34
    Xna
    0.33
    cshtml
    0.33
     becauſe
    0.32
     ")");
    0.32
    Activations Density 0.106%

    No Known Activations