Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6103
    Prev
    Next
    INDEX
    Explanations

    attends to the token "great" from the token "deal."

    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
    0:0.05
    1:0.02
    2:0.03
    3:0.02
    4:0.14
    5:0.66
    6:0.02
    7:0.02
    Negative Logits
     FetchType
    -0.63
    󠁢
    -0.54
     pymongo
    -0.50
     useNavigate
    -0.48
     Dicapai
    -0.45
     ویکی‌پدیای
    -0.44
    enumi
    -0.44
    numerusform
    -0.44
     asiática
    -0.43
     CascadeType
    -0.43
    POSITIVE LOGITS
    LabelTagHelper
    0.52
    aarrggbb
    0.51
     propOrder
    0.49
    RegressionTest
    0.47
     tartalomajánló
    0.46
     the
    0.44
    oredCriteria
    0.43
     estekak
    0.42
     and
    0.40
     she
    0.39
    Activations Density 4.905%

    No Known Activations