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. 7
    Prev
    Next
    INDEX
    Explanations

    attends to specific code symbols and punctuation from coded input types

    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
    0:0.75
    1:0.03
    2:0.02
    3:0.01
    4:0.07
    5:0.02
    6:0.02
    7:0.03
    Negative Logits
     tavola
    -0.30
     supérieurs
    -0.29
     sanitaires
    -0.28
     supérieures
    -0.28
     varandra
    -0.28
     privées
    -0.28
     urbanas
    -0.27
     juridiques
    -0.27
     humaines
    -0.27
     difficiles
    -0.27
    POSITIVE LOGITS
    RenderAtEndOf
    0.53
     مشين
    0.51
     disponibilités
    0.45
    invokeLater
    0.44
    AnimationsModule
    0.43
     ProtoMessage
    0.43
    (!__
    0.42
    曖昧さ回避
    0.42
    urlpatterns
    0.41
     متعلقه
    0.41
    Activations Density 0.022%

    No Known Activations