© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 9715
    Prev
    Next
    INDEX
    Explanations

    expressions related to mathematical operations and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scalatest
    -0.45
     nordic
    -0.42
    ANSA
    -0.41
     ati
    -0.41
    ########.
    -0.40
     relieved
    -0.39
    het
    -0.39
    
    -0.38
     ping
    -0.38
     BR
    -0.38
    POSITIVE LOGITS
    TagMode
    0.72
     Taktlose
    0.59
    RegressionTest
    0.56
    iNdEx
    0.54
     الرياضيه
    0.52
    edicated
    0.51
    ={`
    0.51
    出版年
    0.50
    \{\\
    0.49
     nakalista
    0.49
    Activations Density 0.797%

    No Known Activations