© 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. 20-GEMMASCOPE-RES-16K
    11. 13174
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and treatment outcomes

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

    Text immediately preceding "respectively"

    np_acts-logits-general · gemini-2.0-flash

    lists followed by respectively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flesta
    -0.60
     חיצוניים
    -0.55
     mergeFrom
    -0.54
    ftagPool
    -0.51
     sollte
    -0.51
    的一种
    -0.50
    是一種
    -0.50
    éril
    -0.49
     avoient
    -0.49
    sprozess
    -0.48
    POSITIVE LOGITS
     respectively
    4.00
    respectively
    3.36
     respectivamente
    3.04
     respectivement
    2.55
     соответственно
    2.42
     respec
    2.40
     respective
    2.38
     rispet
    2.25
     correspondingly
    1.81
    respective
    1.80
    Activations Density 0.594%

    No Known Activations