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. 5766
    Prev
    Next
    INDEX
    Explanations

    attends to the token "tax" from unspecified tokens that follow

    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
    0:0.12
    1:0.17
    2:0.11
    3:0.10
    4:0.14
    5:0.06
    6:0.11
    7:0.15
    Negative Logits
     Phry
    -0.27
    FunctionFlags
    -0.26
     Thra
    -0.25
     individuality
    -0.25
     DOP
    -0.24
     Nebu
    -0.24
     viewType
    -0.23
     thofe
    -0.22
     Philist
    -0.22
     SPH
    -0.22
    POSITIVE LOGITS
     سكانية
    0.35
    {}",
    0.31
    슷
    0.31
    )");
    
    0.29
      “
    0.29
    )),
    
    0.29
    ')")
    0.29
    )"),
    0.29
    "));
    
    0.28
    []>(
    0.28
    Activations Density 0.102%

    No Known Activations