© 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. 5470
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal relationships and emotional connections

    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
    othelioma
    -0.47
     aéro
    -0.45
    娶
    -0.45
     natin
    -0.42
    ituary
    -0.42
     vrou
    -0.41
     aanbod
    -0.40
     tł
    -0.40
    ProcessEvent
    -0.39
     reclamo
    -0.38
    POSITIVE LOGITS
     mutually
    0.81
     mutual
    0.75
     inseparable
    0.73
     bonded
    0.70
     exchanging
    0.66
    互
    0.64
     autorytatywna
    0.61
    お互
    0.60
     together
    0.60
     exchanged
    0.60
    Activations Density 0.387%

    No Known Activations