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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6602
    Prev
    Next
    INDEX
    Explanations

    attends to parent-child relationships in structured data representations

    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
    0:0.10
    1:0.11
    2:0.11
    3:0.11
    4:0.12
    5:0.10
    6:0.15
    7:0.16
    Negative Logits
     NDEBUG
    -0.39
     referenties
    -0.37
     vostri
    -0.34
     itſelf
    -0.30
     reaſon
    -0.29
    writeFieldEnd
    -0.29
    neſs
    -0.28
    ChildIndex
    -0.28
    LEncoder
    -0.28
     pleaſure
    -0.27
    POSITIVE LOGITS
     للاسماء
    0.27
    역사
    0.25
    +#+#
    0.25
     насељу
    0.25
    MemoryWarning
    0.24
                
    0.23
     EconPapers
    0.23
    currentColor
    0.23
    awtextra
    0.22
    AccessorTable
    0.22
    Activations Density 0.320%

    No Known Activations