© 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. 12969
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and conditions, particularly those associated with licenses and damages

    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
     nahilalakip
    -0.61
     vérit
    -0.55
     uLocal
    -0.54
     boî
    -0.53
    Véxase
    -0.52
     prêtres
    -0.52
     comportements
    -0.48
     vœux
    -0.47
     négociations
    -0.47
    vânt
    -0.47
    POSITIVE LOGITS
     acids
    0.63
    ilies
    0.59
     các
    0.57
     Hills
    0.57
     gills
    0.56
     hills
    0.56
     joints
    0.56
     valves
    0.55
     fibres
    0.55
     strings
    0.55
    Activations Density 2.305%

    No Known Activations