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. 5861
    Prev
    Next
    INDEX
    Explanations

    attends to the semicolon token from arbitrary tokens, highlighting the need for punctuation or delimiters in code or structured data

    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
    0:0.16
    1:0.25
    2:0.15
    3:0.07
    4:0.11
    5:0.04
    6:0.08
    7:0.09
    Negative Logits
     umani
    -0.54
     Lawler
    -0.48
     africain
    -0.48
     africains
    -0.46
     Micah
    -0.44
     postales
    -0.44
     giuri
    -0.44
     Púb
    -0.44
     urbanas
    -0.43
     sauvages
    -0.42
    POSITIVE LOGITS
    bootstrapcdn
    0.50
    CloseOperation
    0.47
    mybatisplus
    0.44
    AddTagHelper
    0.44
    InputBorder
    0.44
    djangoproject
    0.42
    ########.
    0.41
     المعيارى
    0.40
    SourceChecksum
    0.40
     Hamp
    0.39
    Activations Density 0.042%

    No Known Activations