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. 6053
    Prev
    Next
    INDEX
    Explanations

    attends to instances of "membership" from prepositions indicating the nature of membership

    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
    0:0.60
    1:0.01
    2:0.02
    3:0.03
    4:0.19
    5:0.05
    6:0.02
    7:0.04
    Negative Logits
     Efq
    -0.56
     Houſe
    -0.50
    "},
    
    -0.46
     Majefty
    -0.45
     houſe
    -0.45
     Monfieur
    -0.45
     avoient
    -0.45
     myſelf
    -0.43
    !")
    
    -0.42
     itſelf
    -0.42
    POSITIVE LOGITS
    ↵
    0.35
     "
    0.32
    ↵↵
    0.32
     
    0.29
     pal
    0.28
    signia
    0.28
     he
    0.28
     id
    0.28
     de
    0.27
    NameInMap
    0.27
    Activations Density 0.010%

    No Known Activations