© 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. 25-GEMMASCOPE-RES-16K
    11. 4535
    Prev
    Next
    INDEX
    Explanations

    medical terms related to severe adverse reactions and treatment outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asteroide
    -0.61
     esternos
    -0.60
     joaat
    -0.58
    出版年
    -0.57
    timewa
    -0.57
     Harmony
    -0.56
    enumi
    -0.53
     Wiktionnaire
    -0.53
     lượt
    -0.52
    Practices
    -0.51
    POSITIVE LOGITS
     progression
    0.96
     progress
    0.91
     progressed
    0.90
    progress
    0.88
     Progression
    0.88
    Progression
    0.87
    prog
    0.82
     prog
    0.80
     progressing
    0.79
     progresses
    0.76
    Activations Density 1.480%

    No Known Activations