© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15976
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emotional states and well-being

    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
     невозможно
    -0.52
    どうしても
    -0.48
     schlecht
    -0.46
     нельзя
    -0.45
     špat
    -0.45
    になってしまう
    -0.44
    Poor
    -0.44
     inadequate
    -0.44
     unmöglich
    -0.44
     cannot
    -0.44
    POSITIVE LOGITS
     unharmed
    1.25
     undamaged
    1.09
     intact
    1.07
     perfectly
    1.02
     unaffected
    1.02
     problemlos
    0.99
     happily
    0.98
     satisfactorily
    0.97
     thankfully
    0.93
     perfectamente
    0.91
    Activations Density 1.025%

    No Known Activations