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. 320
    Prev
    Next
    INDEX
    Explanations

    attends to "Korea" from various related tokens that refer to Korea or its associated institutions or concepts

    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
    0:0.62
    1:0.01
    2:0.02
    3:0.06
    4:0.15
    5:0.04
    6:0.02
    7:0.05
    Negative Logits
     שוליים
    -0.39
     المعيارى
    -0.34
     Cæsar
    -0.30
     lordship
    -0.28
     htons
    -0.28
     overthrown
    -0.27
    RTEE
    -0.27
    sizeCache
    -0.27
     الحره
    -0.27
    #![
    -0.27
    POSITIVE LOGITS
    SourceChecksum
    0.30
    السكان
    0.30
    ivir
    0.30
    RetentionPolicy
    0.28
    はじめに
    0.26
    (");
    0.25
    yticks
    0.25
    Erreferentziak
    0.25
    batore
    0.25
    ţă
    0.24
    Activations Density 0.008%

    No Known Activations