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. 1298
    Prev
    Next
    INDEX
    Explanations

    attends to the keys within various data structures from their corresponding values

    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
    2:0.41
    3:0.15
    4:0.01
    5:0.00
    6:0.03
    7:0.03
    8:0.03
    9:0.01
    10:0.01
    11:0.01
    12:0.03
    13:0.03
    14:0.13
    15:0.01
    Negative Logits
    featureID
    -0.84
    parsedMessage
    -0.83
    contentLoaded
    -0.81
    ﹧
    -0.80
    testify
    -0.80
    tagHelperRunner
    -0.79
    <unused43>
    -0.78
    <pad>
    -0.78
     メンテナ
    -0.78
    Personensuche
    -0.78
    POSITIVE LOGITS
     later
    0.39
     the
    0.39
     school
    0.38
     one
    0.37
     files
    0.35
     price
    0.35
     work
    0.34
     down
    0.34
     points
    0.34
     time
    0.34
    Activations Density 0.011%

    No Known Activations