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

    Neuronpedia

    APICircuit 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. 0-GEMMASCOPE-ATT-16K
    6. 135
    Prev
    Next
    INDEX
    Explanations

    attends to technology-related tokens from application-related tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    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
    0:0.41
    1:0.01
    2:0.03
    3:0.02
    4:0.19
    5:0.20
    6:0.01
    7:0.08
    Negative Logits
    R
    -0.36
    Z
    -0.33
    Y
    -0.33
    ところで
    -0.32
    W
    -0.31
     commerciaux
    -0.30
    tagHelperRunner
    -0.29
     comerciales
    -0.29
     R
    -0.29
    K
    -0.29
    POSITIVE LOGITS
    writeFieldEnd
    0.55
     Мексичка
    0.54
    orianCalendar
    0.48
     myſelf
    0.46
    NUMX
    0.44
     AssemblyTitle
    0.43
     cdti
    0.42
     '\\;'
    0.42
     beginnetje
    0.42
    Хьажоргаш
    0.41
    Activations Density 0.014%

    No Known Activations