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. 5792
    Prev
    Next
    INDEX
    Explanations

    attends to licensing and copyright-related tokens from related tokens indicating types of licenses

    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
    0:0.15
    1:0.23
    2:0.13
    3:0.06
    4:0.12
    5:0.03
    6:0.08
    7:0.17
    Negative Logits
     yii
    -0.28
    CloseOperation
    -0.27
     Fuer
    -0.26
     Ramadhan
    -0.24
     Moro
    -0.23
     rück
    -0.23
     Daz
    -0.23
     Mora
    -0.23
    verse
    -0.23
     ros
    -0.22
    POSITIVE LOGITS
    />";
    0.38
    modelBuilder
    0.37
    اریخ
    0.37
     насељу
    0.34
    كويكب
    0.33
    IUrlHelper
    0.32
     esterni
    0.32
    الإنجليزية
    0.32
     <>",
    0.31
    adpleegd
    0.31
    Activations Density 0.205%

    No Known Activations