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. 188
    Prev
    Next
    INDEX
    Explanations

    attends to the token "d" from various tokens labeled with "D" followed by numerical indices

    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
    0:0.10
    1:0.03
    2:0.03
    3:0.05
    4:0.08
    5:0.05
    6:0.06
    7:0.56
    Negative Logits
     myſelf
    -0.58
     Efq
    -0.57
     Jefus
    -0.56
    ſelf
    -0.55
    ſelves
    -0.54
     ་་
    -0.53
     itſelf
    -0.53
     Majefty
    -0.51
     iſt
    -0.50
     themſelves
    -0.49
    POSITIVE LOGITS
    RegressionTest
    0.35
    /
    0.32
    :
    0.29
     tur
    0.27
     my
    0.27
     /
    0.27
     |
    0.26
    <eos>
    0.25
    /?
    0.25
    ↵
    0.24
    Activations Density 0.129%

    No Known Activations