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. 264
    Prev
    Next
    INDEX
    Explanations

    attends to tokens marked as "const" from tokens marked with the symbol "*"

    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
    1:0.03
    2:0.04
    3:0.05
    4:0.04
    5:0.04
    6:0.09
    7:0.64
    Negative Logits
     I
    -0.88
     
    -0.82
     S
    -0.79
     "
    -0.78
     “
    -0.78
     a
    -0.77
     in
    -0.76
     the
    -0.75
     (
    -0.73
     N
    -0.72
    POSITIVE LOGITS
     itſelf
    1.70
     myſelf
    1.68
     Monfieur
    1.61
     Efq
    1.57
     Theſe
    1.56
     pleaſure
    1.55
     Jefus
    1.53
     purpoſe
    1.52
     houſe
    1.49
     ſche
    1.48
    Activations Density 0.189%

    No Known Activations