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-2-9B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 1285
    Prev
    Next
    INDEX
    Explanations

    attends to section identifiers from the corresponding identifier within the legal context

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-att/layer_0/width_16k/average_l0_61
    Prompts (Dashboard)
    16,384 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
    0:0.01
    1:0.01
    2:0.01
    3:0.02
    4:0.01
    5:0.01
    6:0.63
    7:0.02
    8:0.02
    9:0.01
    10:0.01
    11:0.01
    12:0.01
    13:0.02
    14:0.05
    15:0.07
    Negative Logits
      
    -0.30
    GRANTED
    -0.29
     An
    -0.28
     A
    -0.27
     "
    -0.25
     The
    -0.24
    ExecuteReader
    -0.24
     All
    -0.24
       
    -0.23
    An
    -0.23
    POSITIVE LOGITS
    MessageOf
    0.33
    uxxxx
    0.32
     disambiguazione
    0.32
     autorytatywna
    0.28
    aarrggbb
    0.25
    PreferredItem
    0.25
    verifyException
    0.24
     kasarigan
    0.24
     informée
    0.23
     surla
    0.23
    Activations Density 0.077%

    No Known Activations