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. 5644
    Prev
    Next
    INDEX
    Explanations

    attends to the pattern of "import" from various later 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
    0:0.09
    1:0.13
    2:0.14
    3:0.06
    4:0.10
    5:0.03
    6:0.10
    7:0.29
    Negative Logits
    bootstrapcdn
    -0.45
    mybatisplus
    -0.45
     }}"></
    -0.44
    amaño
    -0.41
     AssemblyProduct
    -0.40
     BrowserModule
    -0.37
     незавершена
    -0.37
     المعيارى
    -0.36
    CopyWith
    -0.36
     ComVisible
    -0.36
    POSITIVE LOGITS
     makers
    0.25
    See
    0.25
    m
    0.25
    RenderAtEndOf
    0.25
    rsiniz
    0.25
     Handwerk
    0.24
     saites
    0.23
     vigueur
    0.23
     affichés
    0.23
    erek
    0.23
    Activations Density 0.109%

    No Known Activations