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. 20
    Prev
    Next
    INDEX
    Explanations

    attends to instances of the token "my" from instances of the token "my."

    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
    0:0.02
    1:0.73
    2:0.06
    3:0.02
    4:0.04
    5:0.03
    6:0.02
    7:0.05
    Negative Logits
     Савезне
    -0.73
     ProtoMessage
    -0.64
     estekak
    -0.64
    IntoConstraints
    -0.63
    AsUp
    -0.63
    Vidite
    -0.62
    expandindo
    -0.59
     Roskov
    -0.57
    OGND
    -0.57
     Paglinawan
    -0.56
    POSITIVE LOGITS
     the
    0.45
     of
    0.36
    ↵↵
    0.35
     
    0.33
    ,
    0.33
     to
    0.32
    the
    0.31
     along
    0.31
     that
    0.31
     and
    0.30
    Activations Density 0.132%

    No Known Activations