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. 5789
    Prev
    Next
    INDEX
    Explanations

    attends to the last spoken words from a prior speaker up to the point of a new speaker's introduction

    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
    0:0.09
    1:0.14
    2:0.19
    3:0.09
    4:0.09
    5:0.09
    6:0.06
    7:0.20
    Negative Logits
    expandindo
    -0.58
     Normdatei
    -0.48
    sidemargin
    -0.47
     oprot
    -0.45
     ویکی‌پدی
    -0.45
    __':
    
    -0.43
     تضيفلها
    -0.42
     jspb
    -0.42
     ligiloj
    -0.42
     estekak
    -0.41
    POSITIVE LOGITS
    <h1>
    0.26
    \
    0.22
    Past
    0.21
    (
    0.20
     Past
    0.20
    Real
    0.20
    <h2>
    0.19
     plain
    0.19
     /
    0.18
    In
    0.18
    Activations Density 0.017%

    No Known Activations