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. 277
    Prev
    Next
    INDEX
    Explanations

    attends to the term "setup" from various specialized contexts, indicating its importance in establishing configurations or frameworks across different subjects

    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
    0:0.66
    1:0.01
    2:0.01
    3:0.02
    4:0.15
    5:0.04
    6:0.02
    7:0.05
    Negative Logits
     moschino
    -0.34
     Diſ
    -0.33
     ſta
    -0.32
     Efq
    -0.30
     kea
    -0.29
     ſtre
    -0.29
    CodeAnalysis
    -0.29
     Mev
    -0.28
     Estar
    -0.28
     Conſ
    -0.27
    POSITIVE LOGITS
     nakalista
    0.74
     propOrder
    0.64
    RenderAtEndOf
    0.58
    الحياه
    0.57
     ModelExpression
    0.52
    RegistryLite
    0.51
     surla
    0.50
     '\\;'
    0.48
     linkovi
    0.47
     disambiguazione
    0.47
    Activations Density 0.005%

    No Known Activations