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. 76
    Prev
    Next
    INDEX
    Explanations

    attends to the token "io" from various instances of tokens marked with "io."

    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
    0:0.02
    1:0.40
    2:0.27
    3:0.02
    4:0.03
    5:0.05
    6:0.03
    7:0.13
    Negative Logits
    can
    -0.24
    io
    -0.23
    us
    -0.21
    Can
    -0.21
    ·
    -0.20
    ui
    -0.19
    To
    -0.19
    ■
    -0.19
    Us
    -0.18
    in
    -0.18
    POSITIVE LOGITS
     متعلقه
    0.50
    __":
    
    0.49
    InjectAttribute
    0.48
    TagMode
    0.45
    __':
    
    0.45
    MemoryWarning
    0.42
     AssemblyCulture
    0.40
     ***!
    0.39
    +#+#
    0.39
    forChild
    0.39
    Activations Density 0.025%

    No Known Activations