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. 0-GEMMASCOPE-ATT-16K
    6. 358
    Prev
    Next
    INDEX
    Explanations

    attends to height-related tokens from a range of subsequent tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 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
    0:0.04
    1:0.01
    2:0.01
    3:0.07
    4:0.73
    5:0.04
    6:0.02
    7:0.03
    Negative Logits
     
    -0.39
    6
    -0.36
    (
    -0.36
    0
    -0.36
    8
    -0.36
    2
    -0.36
    7
    -0.36
    1
    -0.36
    3
    -0.35
    4
    -0.34
    POSITIVE LOGITS
    Tembelea
    0.74
    DockStyle
    0.74
     InputDecoration
    0.68
    AddTagHelper
    0.68
    </caption>
    0.68
    ConstraintMaker
    0.67
     himo
    0.66
     متعلقه
    0.66
    ValueStyle
    0.66
    )";
    
    0.65
    Activations Density 0.041%

    No Known Activations