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. 1366
    Prev
    Next
    INDEX
    Explanations

    attends to the plural-related tokens from singular-related tokens

    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
    1:0.01
    2:0.06
    3:0.03
    4:0.02
    5:0.02
    6:0.04
    7:0.04
    8:0.01
    9:0.02
    10:0.02
    11:0.03
    12:0.04
    13:0.06
    14:0.46
    15:0.04
    Negative Logits
     queſta
    -0.89
     ſind
    -0.88
     ſta
    -0.88
     myſelf
    -0.87
    <unused68>
    -0.82
     ſch
    -0.82
     faſt
    -0.82
    <unused52>
    -0.82
    <unused8>
    -0.82
    <unused21>
    -0.82
    POSITIVE LOGITS
     civilización
    0.33
     productividad
    0.32
     integridad
    0.32
     legislación
    0.31
    1
    0.31
    2
    0.29
     estabilidad
    0.28
    3
    0.28
    accompagnement
    0.28
     ciudadanía
    0.27
    Activations Density 0.060%

    No Known Activations