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. 10-GEMMASCOPE-ATT-16K
    6. 6106
    Prev
    Next
    INDEX
    Explanations

    attends to possessive tokens from their related subjects or pronouns

    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
    0:0.11
    1:0.12
    2:0.14
    3:0.07
    4:0.06
    5:0.02
    6:0.11
    7:0.32
    Negative Logits
    Riley
    -0.32
     Siehe
    -0.31
     Metzger
    -0.31
     fato
    -0.30
     normaux
    -0.30
     connexes
    -0.30
    klart
    -0.29
     eletrônico
    -0.29
    ざる
    -0.28
     françaises
    -0.28
    POSITIVE LOGITS
    expandindo
    0.38
    parsedMessage
    0.36
     Réponses
    0.36
     MainAxisSize
    0.34
    VersionUID
    0.33
    
    0.32
    msgTypes
    0.32
    قایناقلار
    0.32
    vician
    0.31
    вач
    0.31
    Activations Density 0.488%

    No Known Activations