© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 13302
    Prev
    Next
    INDEX
    Explanations

    variations of the word "sum" and related terms in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    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

    Negative Logits
     içinde
    -0.34
     effectively
    -0.33
    rough
    -0.33
     intervened
    -0.33
    värr
    -0.33
     formie
    -0.32
     województwie
    -0.32
    weis
    -0.32
    ante
    -0.32
     בב
    -0.31
    POSITIVE LOGITS
     sum
    1.05
     SUM
    0.90
     Sum
    0.85
    sum
    0.84
    Sum
    0.82
     sums
    0.81
    SUM
    0.79
    sums
    0.78
     summing
    0.77
    parsedMessage
    0.73
    Activations Density 0.202%

    No Known Activations