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. 6035
    Prev
    Next
    INDEX
    Explanations

    attends to specific instances of the token "N" from various indexed digits appearing later in the sequence

    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
    0:0.03
    1:0.02
    2:0.02
    3:0.02
    4:0.06
    5:0.02
    6:0.03
    7:0.75
    Negative Logits
     Мексичка
    -0.64
    OGND
    -0.64
     Савезне
    -0.60
    onAttach
    -0.56
    astéroïdes
    -0.55
    ^(@)
    -0.54
     تضيفلها
    -0.54
    __":
    
    -0.54
     שוליים
    -0.53
    .")
    
    -0.53
    POSITIVE LOGITS
     
    0.37
    1
    0.36
    6
    0.34
    <strong>
    0.33
    <eos>
    0.33
    3
    0.32
    4
    0.31
    5
    0.31
    2
    0.31
    ↵↵
    0.30
    Activations Density 0.247%

    No Known Activations