Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Attention Out - 16k
    5. 10-GEMMASCOPE-ATT-16K
    6. 5529
    Prev
    Next
    INDEX
    Explanations

    attends to the inclusive pronoun "our" from token references to "we."

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.18
    2:0.05
    3:0.05
    4:0.11
    5:0.42
    6:0.06
    7:0.04
    Negative Logits
     Paglinawan
    -0.30
    存于互联网档案馆
    -0.28
    ății
    -0.27
    athione
    -0.26
    irtschaft
    -0.26
    optera
    -0.26
    Mots
    -0.25
    audiovisuel
    -0.24
    rijven
    -0.24
    ฬ
    -0.24
    POSITIVE LOGITS
    האם
    0.26
     ही
    0.25
     ہی
    0.23
     برانيه
    0.22
     وتسجيلات
    0.22
    それとも
    0.22
     unknownFields
    0.21
    IonicModule
    0.21
     gepubliceerd
    0.21
     fact
    0.21
    Activations Density 0.050%

    No Known Activations