© 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. 2-GEMMASCOPE-RES-16K
    11. 12741
    Prev
    Next
    INDEX
    Explanations

    references to symptoms in medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.60
     surla
    -0.50
     GenerationType
    -0.48
    WriteTagHelper
    -0.47
    PerformLayout
    -0.46
    multer
    -0.46
    帖最后由
    -0.45
    DIPSETTING
    -0.45
     števil
    -0.45
    出版年
    -0.44
    POSITIVE LOGITS
     ACCUR
    0.75
     symptoms
    0.73
     fatal
    0.73
     accuracy
    0.73
     symptom
    0.71
     Accuracy
    0.69
    Symptoms
    0.68
     Symptom
    0.67
    Accuracy
    0.67
     accurate
    0.66
    Activations Density 0.108%

    No Known Activations