© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3603
    Prev
    Next
    INDEX
    Explanations

    terms related to medical assessments of pain and associated conditions

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

    surrounding "pain"

    np_acts-logits-general · gemini-2.0-flash

    pain and discomfort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Folio
    -0.55
     impea
    -0.54
    arella
    -0.53
    Rhestr
    -0.51
    atern
    -0.51
    SLOT
    -0.50
     impeach
    -0.49
    комиться
    -0.49
    rungsseite
    -0.47
     ^{-
    -0.46
    POSITIVE LOGITS
     pain
    2.59
     Pain
    2.26
    Pain
    2.22
    pain
    2.16
     PAIN
    2.09
     painful
    1.87
     pains
    1.85
     douleur
    1.73
     pijn
    1.70
     Schmerzen
    1.60
    Activations Density 0.620%

    No Known Activations