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-2-9B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 1214
    Prev
    Next
    INDEX
    Explanations

    attends to language-related tokens from time indicators

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-att/layer_0/width_16k/average_l0_61
    Prompts (Dashboard)
    16,384 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
    0:0.01
    1:0.02
    2:0.48
    3:0.04
    4:0.00
    5:0.00
    6:0.02
    7:0.03
    8:0.01
    9:0.02
    10:0.01
    11:0.01
    12:0.01
    13:0.18
    14:0.09
    15:0.01
    Negative Logits
    
    -0.45
     Administrativna
    -0.41
     propOrder
    -0.40
     Савезне
    -0.38
    SpringBootTest
    -0.37
     تضيفلها
    -0.36
     transfieras
    -0.36
     ویکی‌پدی
    -0.35
    httphttps
    -0.35
    +:+
    -0.34
    POSITIVE LOGITS
    :✨
    0.16
     Pit
    0.16
     which
    0.15
     Á
    0.14
     Shi
    0.14
     Pole
    0.14
     Card
    0.14
     them
    0.13
     waste
    0.13
     Ju
    0.13
    Activations Density 0.150%

    No Known Activations