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. 1343
    Prev
    Next
    INDEX
    Explanations

    attends to tokens labeled "Ja" from tokens labeled "far" located 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
    0:0.05
    1:0.04
    2:0.02
    3:0.03
    4:0.05
    5:0.03
    6:0.04
    7:0.04
    8:0.04
    9:0.04
    10:0.03
    11:0.05
    12:0.29
    13:0.13
    14:0.04
    15:0.01
    Negative Logits
    <unused43>
    -1.38
    <unused17>
    -1.38
    <unused28>
    -1.38
    <pad>
    -1.38
    <unused41>
    -1.38
    <unused47>
    -1.38
    <unused42>
    -1.38
    <unused74>
    -1.38
    [@BOS@]
    -1.37
    <unused3>
    -1.37
    POSITIVE LOGITS
     Económica
    0.60
     laikā
    0.57
     oídos
    0.56
     varandra
    0.54
     istrinya
    0.53
     gwaran
    0.52
     ibunya
    0.52
     cesty
    0.52
     suaminya
    0.52
     hlavy
    0.52
    Activations Density 0.006%

    No Known Activations