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. 1193
    Prev
    Next
    INDEX
    Explanations

    attends to tokens connected by the conjunction "&" from tokens that appear later in the sequence

    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
    0:0.02
    1:0.00
    2:0.01
    3:0.73
    4:0.01
    5:0.02
    6:0.01
    7:0.01
    8:0.01
    9:0.01
    10:0.01
    11:0.02
    12:0.01
    13:0.01
    14:0.05
    15:0.00
    Negative Logits
     zijne
    -0.75
    parsedMessage
    -0.69
     mijne
    -0.66
     disambiguazione
    -0.65
    IsContent
    -0.62
    contentLoaded
    -0.57
    SequentialGroup
    -0.56
     '\\;'
    -0.55
     utafitiHapana
    -0.54
    ConstraintMaker
    -0.54
    POSITIVE LOGITS
     (
    0.50
     “
    0.48
     to
    0.44
     a
    0.42
     "
    0.42
     
    0.42
      
    0.41
     na
    0.41
     and
    0.40
     of
    0.40
    Activations Density 0.082%

    No Known Activations