© 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-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 8735
    Prev
    Next
    INDEX
    Explanations

    terms related to pain management and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eseorang
    -0.56
     fusca
    -0.42
     latas
    -0.41
     antemano
    -0.40
     virtù
    -0.40
     sendok
    -0.39
     đảo
    -0.38
     scouting
    -0.38
     kalın
    -0.38
     dök
    -0.37
    POSITIVE LOGITS
     pain
    1.34
    Pain
    1.28
     Pain
    1.28
    pain
    1.25
     PAIN
    1.13
     douleur
    1.09
     pijn
    1.04
     dolor
    0.99
     pains
    0.99
     painful
    0.98
    Activations Density 0.271%

    No Known Activations