© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4744
    Prev
    Next
    INDEX
    Explanations

    references to demographics, particularly age and sex, in medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Age information, often followed by "old"

    np_acts-logits-general · gemini-2.0-flash

    age and sex descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     age
    -1.00
     aged
    -0.99
     Age
    -0.93
    Age
    -0.90
     ages
    -0.84
     Aged
    -0.80
    age
    -0.80
    Aged
    -0.76
     Ages
    -0.74
    Ages
    -0.73
    POSITIVE LOGITS
    FirstResponder
    0.62
    SourceChecksum
    0.56
    Hauptartikel
    0.53
    prakti
    0.52
    nonatomic
    0.51
     Roskov
    0.51
     idéia
    0.50
    CharField
    0.50
     AssemblyTitle
    0.50
     inclusive
    0.49
    Activations Density 0.261%

    No Known Activations