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

    Neuronpedia

    APICircuit 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. 0-GEMMASCOPE-ATT-16K
    6. 462
    Prev
    Next
    INDEX
    Explanations

    attends to the earlier tokens marked by asterisks from later tokens marked by square brackets

    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
    0:0.05
    1:0.03
    2:0.04
    3:0.03
    4:0.66
    5:0.04
    6:0.07
    7:0.04
    Negative Logits
     onDestroy
    -0.29
    ())){
    -0.28
    _),
    -0.28
    ilan
    -0.28
    cot
    -0.28
    yn
    -0.28
    undet
    -0.27
    Rüyada
    -0.27
    íficos
    -0.26
    ον
    -0.26
    POSITIVE LOGITS
     يتيمه
    0.51
     BorderRadius
    0.48
    WriteBarrier
    0.41
    ГЛА
    0.38
    quelize
    0.38
     BoxFit
    0.37
    LabelTagHelper
    0.37
    ::_('
    0.37
    TintMode
    0.34
    NSNotification
    0.34
    Activations Density 0.179%

    No Known Activations