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-2-9B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 1233
    Prev
    Next
    INDEX
    Explanations

    attends to references to "Chapter" from various tokens that are not displayed, indicating a focus on organizational structures or sections within documents

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-att/layer_0/width_16k/average_l0_61
    Prompts (Dashboard)
    16,384 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
    0:0.01
    1:0.55
    2:0.11
    3:0.01
    4:0.00
    5:0.00
    6:0.03
    7:0.02
    8:0.01
    9:0.02
    10:0.03
    11:0.01
    12:0.01
    13:0.04
    14:0.05
    15:0.01
    Negative Logits
     
    -0.40
    ;
    -0.35
    '
    -0.33
    {
    -0.27
     the
    -0.26
     I
    -0.25
    ↵↵
    -0.25
    ↵
    -0.24
    1
    -0.23
     "
    -0.23
    POSITIVE LOGITS
    <unused41>
    2.00
    <unused14>
    2.00
    <unused43>
    2.00
    <unused79>
    2.00
    <unused52>
    2.00
    <unused8>
    1.99
    <unused16>
    1.99
    <unused3>
    1.99
    <pad>
    1.99
    [@BOS@]
    1.99
    Activations Density 0.058%

    No Known Activations