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. 6617
    Prev
    Next
    INDEX
    Explanations

    attends to year markings from adjacent tokens where the context of music and production is discussed

    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
    0:0.08
    1:0.12
    2:0.09
    3:0.12
    4:0.22
    5:0.15
    6:0.09
    7:0.10
    Negative Logits
     étrangère
    -0.32
     "..\..\
    -0.32
    udahan
    -0.31
    GOTREF
    -0.30
     pédagogique
    -0.29
     democracia
    -0.28
     Teknologi
    -0.28
     niega
    -0.28
    Hozzáférés
    -0.27
     littéraire
    -0.27
    POSITIVE LOGITS
    /**
    0.39
    onOptions
    0.38
    neſs
    0.35
    Xna
    0.32
    XmlType
    0.32
     Litt
    0.31
    bourhood
    0.30
     useAppContext
    0.30
    kev
    0.30
    letal
    0.30
    Activations Density 0.028%

    No Known Activations