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. 6127
    Prev
    Next
    INDEX
    Explanations

    attends to the reasons for action or benefits of understanding from the corresponding consequence or application of those actions

    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
    1:0.12
    2:0.12
    3:0.11
    4:0.05
    5:0.03
    6:0.12
    7:0.31
    Negative Logits
    SharedDtor
    -0.49
    AndEndTag
    -0.46
    +#+#
    -0.42
     typelib
    -0.41
     تضيفلها
    -0.38
     onBind
    -0.38
     '',
    
    -0.37
     ***!
    -0.37
     ostavi
    -0.37
    IsContent
    -0.36
    POSITIVE LOGITS
    ubuntu
    0.28
    ποτε
    0.27
     enda
    0.26
    拉克
    0.26
     redondo
    0.26
     either
    0.25
    cassandra
    0.25
    躇
    0.25
    qus
    0.25
    iop
    0.24
    Activations Density 0.364%

    No Known Activations