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. 6404
    Prev
    Next
    INDEX
    Explanations

    attends to prepositions or adjectives related to locations or conditions from specific named or definable locations

    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
    1:0.10
    2:0.11
    3:0.06
    4:0.04
    5:0.02
    6:0.07
    7:0.46
    Negative Logits
    tanleria
    -0.33
     resourceCulture
    -0.32
    MENAFN
    -0.29
    Fordítás
    -0.28
    numerusform
    -0.28
    :]:
    -0.28
    tagext
    -0.27
     <>",
    -0.27
    Données
    -0.26
    currentColor
    -0.26
    POSITIVE LOGITS
     next
    0.39
     prochain
    0.34
    next
    0.33
     tomorrow
    0.32
     nächste
    0.31
    下一篇
    0.28
     näch
    0.28
     someday
    0.26
     nächsten
    0.26
    нибудь
    0.26
    Activations Density 0.847%

    No Known Activations