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. 6130
    Prev
    Next
    INDEX
    Explanations

    attends to the width property from percentage values related to different elements

    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
    0:0.14
    1:0.13
    2:0.41
    3:0.06
    4:0.05
    5:0.06
    6:0.03
    7:0.09
    Negative Logits
    awtextra
    -0.50
     considérons
    -0.45
    şiv
    -0.41
     viewDidLoad
    -0.41
    PRWEB
    -0.40
    Datuak
    -0.40
    DockStyle
    -0.39
     CURIAM
    -0.39
    appliquer
    -0.38
    原始内容存档于
    -0.38
    POSITIVE LOGITS
     dass
    0.28
     a
    0.27
    NewLine
    0.26
     ModelExpression
    0.26
     רבים
    0.25
    شة
    0.25
     corner
    0.25
    不少
    0.24
    стероид
    0.24
     end
    0.24
    Activations Density 0.066%

    No Known Activations