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. 0-GEMMASCOPE-ATT-16K
    6. 273
    Prev
    Next
    INDEX
    Explanations

    attends to the acronym "EU" from source-related tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    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
    0:0.58
    1:0.02
    2:0.02
    3:0.04
    4:0.18
    5:0.06
    6:0.02
    7:0.05
    Negative Logits
     surla
    -0.41
    ########.
    -0.36
     pinulongan
    -0.35
     estekak
    -0.30
    
    -0.29
     ou
    -0.29
    MethodManager
    -0.28
    photobucket
    -0.28
    -
    -0.28
    RenderAtEndOf
    -0.28
    POSITIVE LOGITS
     myſelf
    0.46
     bershka
    0.40
     cdti
    0.39
     uſed
    0.39
     Forumite
    0.39
    VERTISEMENT
    0.39
     itſelf
    0.39
    ."));
    0.38
     Efq
    0.38
     faſt
    0.37
    Activations Density 0.010%

    No Known Activations