Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9403
    Prev
    Next
    INDEX
    Explanations

    references to pain management and opioid-related medications

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

    medical terminology and discussions related to pain management, particularly focusing on medical conditions, symptoms, medications like methadone, and the complex interactions between pain and mental health.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    medical and pain-related terminology, particularly words related to pain management, medications, and treatment protocols.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OCCURRED
    -0.57
    ScopeManager
    -0.54
     CreateTagHelper
    -0.53
    Бахар
    -0.52
     nahilalakip
    -0.50
    enterOuterAlt
    -0.49
    MLLoader
    -0.49
    AccessorTable
    -0.48
     ujednoznacz
    -0.47
     measles
    -0.45
    POSITIVE LOGITS
     pain
    2.36
     Pain
    2.13
    Pain
    2.06
    pain
    1.95
     PAIN
    1.78
     douleur
    1.76
     Schmerz
    1.66
     painful
    1.63
     pijn
    1.57
     pains
    1.53
    Activations Density 0.632%

    No Known Activations