© 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. 36-GEMMASCOPE-RES-16K
    11. 10148
    Prev
    Next
    INDEX
    Explanations

    terms related to legal frameworks and concepts

    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
    XmlType
    -0.44
    ronpa
    -0.39
    ONAUT
    -0.38
    gäng
    -0.37
    witzerland
    -0.36
    諷
    -0.36
    anstalt
    -0.36
     Dress
    -0.35
    efined
    -0.34
     zalo
    -0.34
    POSITIVE LOGITS
     upon
    1.35
    Upon
    1.23
     Upon
    1.16
    upon
    1.16
     UPON
    1.15
     auquel
    1.10
     waarop
    1.03
     auxquels
    1.02
     auxquelles
    1.02
     waarmee
    0.84
    Activations Density 0.620%

    No Known Activations