Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6424
    Prev
    Next
    INDEX
    Explanations

    attends to decade-related tokens marked by years from the connecting dash tokens

    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
    0:0.08
    1:0.11
    2:0.09
    3:0.10
    4:0.10
    5:0.08
    6:0.19
    7:0.20
    Negative Logits
    Referencias
    -0.22
    chtete
    -0.21
     rah
    -0.21
     lenker
    -0.21
    tanleria
    -0.20
    仰
    -0.20
     /><
    -0.20
    ispiel
    -0.19
    jillo
    -0.19
    krivning
    -0.19
    POSITIVE LOGITS
     ainfi
    0.40
    Personensuche
    0.39
     defStyle
    0.38
     enfans
    0.37
     estimés
    0.37
    MemoryWarning
    0.36
     étoit
    0.35
    Portale
    0.35
    BrowserModule
    0.35
     inconnu
    0.35
    Activations Density 0.008%

    No Known Activations