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. 1304
    Prev
    Next
    INDEX
    Explanations

    attends to references to articles from repeated mentions of articles

    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
    0:0.03
    1:0.02
    2:0.01
    3:0.11
    4:0.45
    5:0.02
    6:0.02
    7:0.02
    8:0.02
    9:0.01
    10:0.03
    11:0.03
    12:0.11
    13:0.03
    14:0.01
    15:0.01
    Negative Logits
     zijne
    -1.15
     miniaturka
    -1.14
     Italij
    -1.13
     desmotivaciones
    -1.13
     ainfi
    -1.10
     plufieurs
    -1.08
     enfans
    -1.06
     étoient
    -1.06
     Wikiseite
    -1.04
     Monfieur
    -1.01
    POSITIVE LOGITS
    .
    0.90
    sp
    0.87
    ac
    0.86
     
    0.86
    ic
    0.85
    f
    0.85
    ing
    0.85
    w
    0.85
    es
    0.84
    um
    0.84
    Activations Density 0.041%

    No Known Activations