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. 1361
    Prev
    Next
    INDEX
    Explanations

    attends to empty token patterns from various segments of code

    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
    0:0.10
    1:0.20
    2:0.01
    3:0.02
    4:0.05
    5:0.02
    6:0.03
    7:0.05
    8:0.12
    9:0.05
    10:0.09
    11:0.01
    12:0.03
    13:0.07
    14:0.02
    15:0.05
    Negative Logits
    .
    -0.63
     
    -0.45
    ↵↵
    -0.36
    1
    -0.30
    ↵
    -0.30
    ;
    -0.29
    '
    -0.28
     (
    -0.27
    2
    -0.27
    -
    -0.26
    POSITIVE LOGITS
    <unused43>
    2.75
    <unused41>
    2.73
    <unused17>
    2.73
    <pad>
    2.73
    <unused42>
    2.73
    <unused74>
    2.73
    <unused8>
    2.72
    <unused14>
    2.72
    <unused3>
    2.72
    [@BOS@]
    2.72
    Activations Density 0.002%

    No Known Activations