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. 6141
    Prev
    Next
    INDEX
    Explanations

    attends to closing tbody tags from list item tokens

    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
    1:0.12
    2:0.06
    3:0.10
    4:0.05
    5:0.03
    6:0.52
    7:0.07
    Negative Logits
    </h5>
    -0.67
    ."</
    -0.60
    </s>
    -0.57
    </blockquote>
    -0.54
    </u>
    -0.54
    </h6>
    -0.53
     \\
    -0.53
    </i>
    -0.53
    ArgsConstructor
    -0.50
    </th>
    -0.50
    POSITIVE LOGITS
    expandindo
    0.59
     wikipagina
    0.56
    Composable
    0.50
     okuyayım
    0.49
    :✨
    0.48
     vectorielles
    0.48
     &___
    0.47
     stället
    0.47
     récentes
    0.46
     mourut
    0.45
    Activations Density 0.045%

    No Known Activations