© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 2693
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to health and medical symptoms, particularly focusing on psychological and physical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    檚
    -0.62
     was
    -0.59
    큽
    -0.56
    ahuje
    -0.52
     бъде
    -0.49
     начинает
    -0.47
     می‌گوید
    -0.46
    ிறது
    -0.46
    릅
    -0.46
    issait
    -0.45
    POSITIVE LOGITS
     are
    2.69
     have
    1.77
     were
    1.73
     aren
    1.66
     estão
    1.51
     jsou
    1.48
     έχουν
    1.46
     são
    1.39
     имеют
    1.36
     nejsou
    1.36
    Activations Density 6.162%

    No Known Activations