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. 267
    Prev
    Next
    INDEX
    Explanations

    attends to instances of "worse" from subsequent mentions of "than."

    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
    0:0.51
    1:0.02
    2:0.02
    3:0.01
    4:0.27
    5:0.08
    6:0.01
    7:0.04
    Negative Logits
     protoimpl
    -0.29
    babwe
    -0.28
    OfWork
    -0.27
    üyada
    -0.26
     Uniti
    -0.26
    irmanship
    -0.25
    dafx
    -0.25
     times
    -0.25
     circumstances
    -0.25
     adult
    -0.25
    POSITIVE LOGITS
    findpost
    0.42
     vectorielles
    0.42
    httphttps
    0.40
    noinspection
    0.40
    ftagPool
    0.39
    IsContent
    0.39
     recommandée
    0.39
     @"/
    0.38
    商品説明
    0.37
     상세
    0.37
    Activations Density 0.009%

    No Known Activations