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. 6027
    Prev
    Next
    INDEX
    Explanations

    attends to contexts involving foreign matters from related affairs

    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
    0:0.12
    1:0.04
    2:0.04
    3:0.02
    4:0.42
    5:0.21
    6:0.02
    7:0.09
    Negative Logits
     leaſt
    -0.63
     uſed
    -0.60
     Monfieur
    -0.59
     theſe
    -0.59
     houſe
    -0.58
     ſeveral
    -0.57
     uſe
    -0.57
     becauſe
    -0.57
     whoſe
    -0.56
    出版年
    -0.56
    POSITIVE LOGITS
     \&
    0.33
    〈
    0.32
     she
    0.32
    transQ
    0.31
     F
    0.31
    ↵↵
    0.30
    〉
    0.30
     and
    0.30
    vies
    0.29
     st
    0.28
    Activations Density 0.020%

    No Known Activations