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

    Neuronpedia

    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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14016
    Prev
    Next
    INDEX
    Explanations

    concepts related to mental health and relaxation techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    comfort, relief, or relaxation

    np_acts-logits-general · gemini-2.0-flash

    relaxation and escape

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zungs
    -0.38
     defects
    -0.35
    AutoresizingMask
    -0.34
     Defective
    -0.34
    怕
    -0.33
     Defects
    -0.33
    iency
    -0.33
    HomeAsUpEnabled
    -0.32
    guntas
    -0.32
     lia
    -0.31
    POSITIVE LOGITS
     '\\;'
    0.69
     relief
    0.63
     soothing
    0.62
    Relief
    0.62
    relief
    0.62
     calming
    0.61
     solace
    0.60
     успо
    0.59
    calm
    0.59
     calms
    0.59
    Activations Density 0.183%

    No Known Activations