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. 219
    Prev
    Next
    INDEX
    Explanations

    attends to special symbols or formatting marks from the sequence representing mathematical expressions or notation

    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
    1:0.17
    2:0.05
    3:0.04
    4:0.05
    5:0.49
    6:0.09
    7:0.05
    Negative Logits
    '));
    
    -0.59
    '))
    
    -0.56
    "));
    
    -0.54
     */
    
    -0.54
    .
    -0.53
    )));
    
    -0.53
    .
    
    -0.53
     }}$
    -0.52
    >';
    
    -0.52
    ()));
    
    -0.52
    POSITIVE LOGITS
     Efq
    1.10
     myſelf
    1.09
     ſtate
    1.08
     Majefty
    1.06
     purpoſe
    1.05
     itſelf
    1.00
     Reſ
    0.99
     Monfieur
    0.99
     Jefus
    0.99
     Shakspeare
    0.98
    Activations Density 0.009%

    No Known Activations