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. 68
    Prev
    Next
    INDEX
    Explanations

    attends to tokens that are related to "and/or" from various contextual pairs of topics or subjects

    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
    0:0.84
    1:0.01
    2:0.00
    3:0.00
    4:0.08
    5:0.02
    6:0.00
    7:0.00
    Negative Logits
      (
    -0.43
    {}/
    -0.41
    ientôt
    -0.40
    ratulations
    -0.40
    bibfield
    -0.39
    ustimmung
    -0.36
    bibinfo
    -0.36
     see
    -0.36
    iſter
    -0.36
    .~(\
    -0.35
    POSITIVE LOGITS
     universitario
    0.46
     esportivo
    0.40
     universitaria
    0.39
     indipendente
    0.36
     noastră
    0.36
    //
    0.36
     Pilate
    0.35
     Sarm
    0.35
     umano
    0.35
     statunit
    0.35
    Activations Density 2.774%

    No Known Activations