© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 3181
    Prev
    Next
    INDEX
    Explanations

    terms related to patient comfort and support in medical settings

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

    joint posture strength

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     fubject
    -0.78
     ſche
    -0.76
     houſe
    -0.74
     raiſ
    -0.73
     Anſ
    -0.72
     poffe
    -0.72
     anſ
    -0.71
     faſt
    -0.70
     fevere
    -0.68
     ſta
    -0.67
    POSITIVE LOGITS
     postural
    0.71
     posture
    0.63
     Posture
    0.56
     tension
    0.56
     stretch
    0.55
     postura
    0.51
     joint
    0.49
     articulation
    0.49
     bio
    0.48
     imbalances
    0.47
    Activations Density 0.078%

    No Known Activations