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-2-2B
    4. Attention Out - 16k
    5. 10-GEMMASCOPE-ATT-16K
    6. 6058
    Prev
    Next
    INDEX
    Explanations

    attends to the closest value comparisons from mathematical expressions marked by double square brackets

    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
    0:0.07
    1:0.08
    2:0.46
    3:0.08
    4:0.10
    5:0.05
    6:0.05
    7:0.07
    Negative Logits
    uk
    -0.32
     Corea
    -0.32
    ?”
    -0.32
     Gelb
    -0.29
    ваш
    -0.29
     CELL
    -0.29
     blur
    -0.28
    my
    -0.28
     lamb
    -0.28
    ik
    -0.28
    POSITIVE LOGITS
     AssemblyTitle
    0.65
    ValueStyle
    0.58
     дописавши
    0.57
     GenerationType
    0.57
    RegistryLite
    0.56
    ConstraintMaker
    0.55
    SequentialGroup
    0.55
    IANGLES
    0.54
    DockStyle
    0.53
    InjectAttribute
    0.53
    Activations Density 0.131%

    No Known Activations