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. 5738
    Prev
    Next
    INDEX
    Explanations

    attends to numeric values or specific characters represented from a wider context or code snippets

    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
    0:0.07
    1:0.21
    2:0.05
    3:0.07
    4:0.15
    5:0.29
    6:0.05
    7:0.06
    Negative Logits
     خارجية
    -0.50
     JTable
    -0.46
    Източници
    -0.42
     doPost
    -0.38
    Referencies
    -0.37
    feira
    -0.37
     تعدى
    -0.36
    Rujukan
    -0.35
     extérieurs
    -0.35
     extérieur
    -0.35
    POSITIVE LOGITS
     незавершена
    0.44
    ESOME
    0.37
     '../../../../
    0.34
    thums
    0.33
     nakalista
    0.29
     '../../../
    0.29
     '.
    0.29
    "]').
    0.28
    iLocal
    0.28
    ENAME
    0.28
    Activations Density 0.040%

    No Known Activations