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. 124
    Prev
    Next
    INDEX
    Explanations

    attends to the token "constant" from various terms that indicate a dependency on other qualifying 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
    0:0.68
    1:0.01
    2:0.01
    3:0.01
    4:0.16
    5:0.05
    6:0.01
    7:0.02
    Negative Logits
    tagHelperRunner
    -0.46
    GraphicsUnit
    -0.45
    出版年
    -0.43
    :✨
    -0.41
    HtmlAttribute
    -0.41
    reportWebVitals
    -0.40
     للاسماء
    -0.39
    RegressionTest
    -0.38
    raeli
    -0.37
    ########.
    -0.36
    POSITIVE LOGITS
    StackNavigator
    0.31
     horaires
    0.30
    Re
    0.30
    au
    0.29
     neige
    0.29
     clearColor
    0.28
    ve
    0.28
    bar
    0.28
    RectangleBorder
    0.28
     ovunque
    0.28
    Activations Density 0.019%

    No Known Activations