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. 6096
    Prev
    Next
    INDEX
    Explanations

    attends to tokens indicating states or conditions from corresponding tokens that denote qualities or characteristics

    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
    2:0.11
    3:0.12
    4:0.11
    5:0.04
    6:0.13
    7:0.24
    Negative Logits
    lccn
    -0.39
    webElementXpaths
    -0.36
    AsUp
    -0.33
    ]))
    
    -0.33
     виправивши
    -0.32
    identiality
    -0.32
    yntaxException
    -0.32
    odyear
    -0.31
    RetentionPolicy
    -0.31
    toMatchSnapshot
    -0.31
    POSITIVE LOGITS
    formis
    0.26
     intptr
    0.26
    sta
    0.25
    DialogContent
    0.25
     Kej
    0.24
    mtable
    0.24
     lắm
    0.23
    del
    0.23
     umani
    0.23
     समीक्षाएं
    0.22
    Activations Density 0.214%

    No Known Activations