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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6081
    Prev
    Next
    INDEX
    Explanations

    attends to the Java import statements from Java code context

    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
    0:0.01
    1:0.02
    2:0.03
    3:0.02
    4:0.05
    5:0.80
    6:0.02
    7:0.02
    Negative Logits
     itſelf
    -1.95
     Theſe
    -1.91
     ―――――
    -1.89
     Efq
    -1.89
     myſelf
    -1.88
     photolibrary
    -1.75
    ^(@)
    -1.73
     ་་
    -1.72
     doubtnut
    -1.70
     ſind
    -1.67
    POSITIVE LOGITS
    .
    1.33
     
    1.27
    ↵
    1.13
     (
    1.09
    -
    1.05
     and
    1.03
    ,
    1.01
    ;
    1.00
    ↵↵
    0.98
    <eos>
    0.94
    Activations Density 0.081%

    No Known Activations