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. 6112
    Prev
    Next
    INDEX
    Explanations

    attends to the opening HTML tags from the closing HTML tags

    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
    1:0.01
    2:0.03
    3:0.02
    4:0.05
    5:0.76
    6:0.05
    7:0.02
    Negative Logits
    .
    -1.59
    ↵
    -1.59
    ↵↵
    -1.31
     
    -1.27
     (
    -1.20
    ,
    -1.18
    <strong>
    -1.16
    </strong>
    -1.15
      
    -1.12
    </em>
    -1.12
    POSITIVE LOGITS
     myſelf
    2.14
     Efq
    2.11
     Theſe
    2.05
     itſelf
    2.02
     Monfieur
    2.00
     ―――――
    1.95
     Jefus
    1.89
     Anſ
    1.88
    ſelf
    1.84
     Majefty
    1.84
    Activations Density 8.641%

    No Known Activations