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. 470
    Prev
    Next
    INDEX
    Explanations

    attends to forms of meditation or wellness-related tokens from subsequent tokens that imply performing actions or exercises

    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
    0:0.02
    1:0.05
    2:0.05
    3:0.30
    4:0.06
    5:0.07
    6:0.28
    7:0.13
    Negative Logits
     ་་
    -1.20
    )");
    
    -1.17
    )";
    
    -1.13
     itſelf
    -1.10
     ―――――
    -1.09
     doubtnut
    -1.05
    ^(@)
    -1.02
     $_"
    -1.02
     photolibrary
    -1.02
     **/
    
    -1.01
    POSITIVE LOGITS
    ↵
    0.70
     
    0.65
     (
    0.55
    ...
    0.54
     -
    0.53
    ,
    0.51
     to
    0.50
     on
    0.49
     of
    0.47
     s
    0.46
    Activations Density 0.011%

    No Known Activations