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. 10-GEMMASCOPE-ATT-16K
    6. 6051
    Prev
    Next
    INDEX
    Explanations

    attends to conjunctions connecting lists or phrases from related pronouns or tokens later in the sentence

    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
    1:0.10
    2:0.14
    3:0.37
    4:0.08
    5:0.02
    6:0.05
    7:0.08
    Negative Logits
    ]='\
    -0.35
     mắn
    -0.34
    OfMonth
    -0.34
     SCS
    -0.34
      (
    -0.34
    PHONY
    -0.33
    %"),
    -0.33
    bub
    -0.33
    autoload
    -0.32
    ChildScrollView
    -0.32
    POSITIVE LOGITS
     protoimpl
    0.41
     ExecuteAsync
    0.34
    +:+
    0.34
     foglal
    0.31
     ***!
    0.30
    Additions
    0.29
    FunctionFlags
    0.28
    TagMode
    0.28
     REFR
    0.28
    UnknownFieldSet
    0.28
    Activations Density 0.840%

    No Known Activations