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. 6098
    Prev
    Next
    INDEX
    Explanations

    attends to the token "quite" from related tokens that follow it

    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
    0:0.67
    1:0.03
    2:0.02
    3:0.01
    4:0.17
    5:0.03
    6:0.01
    7:0.02
    Negative Logits
     ModelExpression
    -0.43
    
    -0.40
    Enders
    -0.34
    Referanser
    -0.34
    Πηγές
    -0.34
     FetchType
    -0.33
    جستارهای
    -0.33
     ſen
    -0.32
     cauſe
    -0.32
    theless
    -0.32
    POSITIVE LOGITS
     which
    0.39
    URIComponent
    0.37
     Paglinawan
    0.36
    twimg
    0.36
    neté
    0.34
    hilation
    0.32
    ModelBuilder
    0.32
    Configurer
    0.32
     noDo
    0.32
    which
    0.32
    Activations Density 0.050%

    No Known Activations