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. 5845
    Prev
    Next
    INDEX
    Explanations

    attends to various token patterns from numeric values and punctuation marks within relevant contexts

    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
    0:0.10
    1:0.17
    2:0.09
    3:0.06
    4:0.07
    5:0.08
    6:0.17
    7:0.22
    Negative Logits
     I
    -0.33
     (
    -0.26
    الحياه
    -0.26
    strukturen
    -0.25
      
    -0.25
    .
    -0.25
     Cas
    -0.23
    lla
    -0.23
    mical
    -0.23
    ynx
    -0.23
    POSITIVE LOGITS
    AndEndTag
    0.55
    MessageOf
    0.52
    urlpatterns
    0.50
     дописавши
    0.49
    rungsseite
    0.44
     Мексичка
    0.44
    setVerticalGroup
    0.41
    +#+#
    0.41
     GenerationType
    0.41
     initComponents
    0.40
    Activations Density 0.001%

    No Known Activations