© 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. 19-GEMMASCOPE-RES-16K
    11. 15571
    Prev
    Next
    INDEX
    Explanations

    guidelines and precautions related to medication usage, specifically opioids like methadone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fucking
    -0.75
     massive
    -0.75
     ибо
    -0.69
     veritable
    -0.68
     burgeoning
    -0.67
     plethora
    -0.67
     putative
    -0.67
     hapless
    -0.65
    queryInterface
    -0.64
     fucking
    -0.64
    POSITIVE LOGITS
     purpoſe
    1.05
     itſelf
    0.99
     chré
    0.98
     myſelf
    0.94
     étoient
    0.90
     perſon
    0.89
     occaf
    0.89
     reaſon
    0.88
     ſtate
    0.88
     poffible
    0.88
    Activations Density 0.427%

    No Known Activations