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. 187
    Prev
    Next
    INDEX
    Explanations

    attends to the validation question "Is" from the subsequent tokens that follow it

    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
    0:0.03
    1:0.65
    2:0.05
    3:0.03
    4:0.06
    5:0.04
    6:0.05
    7:0.06
    Negative Logits
     ་་
    -0.92
     ―――――
    -0.90
     myſelf
    -0.88
     itſelf
    -0.87
     Monfieur
    -0.79
     Theſe
    -0.78
     Reſ
    -0.77
     Beſ
    -0.74
     Efq
    -0.73
     uſed
    -0.73
    POSITIVE LOGITS
     is
    0.63
     in
    0.56
     to
    0.53
     for
    0.52
     a
    0.52
    ,
    0.51
     or
    0.50
     of
    0.49
    .
    0.49
     the
    0.49
    Activations Density 0.064%

    No Known Activations