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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6431
    Prev
    Next
    INDEX
    Explanations

    attends to color-related tokens from their respective token types appearing later in the sequence

    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
    0:0.11
    1:0.15
    2:0.12
    3:0.11
    4:0.14
    5:0.10
    6:0.09
    7:0.14
    Negative Logits
    willReturn
    -0.26
    flé
    -0.24
     jsPsych
    -0.23
    ciamo
    -0.22
    IntoConstraints
    -0.21
     PhpStorm
    -0.21
     esfuer
    -0.21
    اضي
    -0.21
    QUADS
    -0.21
     skj
    -0.21
    POSITIVE LOGITS
     سكانية
    0.34
    
    0.33
     <<<<<<<<<<<<<<
    0.32
    parsedMessage
    0.31
    IContainer
    0.31
    abetes
    0.31
    Demografía
    0.30
    HtmlAttribute
    0.30
     esternos
    0.29
    setVerticalGroup
    0.29
    Activations Density 0.278%

    No Known Activations