© 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. 36-GEMMASCOPE-RES-16K
    11. 9642
    Prev
    Next
    INDEX
    Explanations

    references to comparisons or contrasting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.87
     EconPapers
    -0.85
     ब्रेकडाउन
    -0.83
    ंदीखरीदारी
    -0.81
    Personensuche
    -0.79
    ьаж
    -0.77
    fromnode
    -0.75
     برانيه
    -0.71
    SequentialGroup
    -0.71
     ModelExpression
    -0.71
    POSITIVE LOGITS
     ď
    0.44
     (...)
    0.42
     inc
    0.39
     cir
    0.35
     mts
    0.35
     ich
    0.34
     miz
    0.34
     (…)
    0.33
     dap
    0.33
     place
    0.32
    Activations Density 1.026%

    No Known Activations