© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12639
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a comparison or relationship between entities

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

    "between"

    np_acts-logits-general · gemini-2.0-flash

    between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     enfans
    -0.70
    mstyle
    -0.61
     âmes
    -0.52
     auroit
    -0.52
    ſelf
    -0.51
     pleaſure
    -0.51
     vœux
    -0.49
    NonQuery
    -0.48
     feroit
    -0.46
     Ruß
    -0.46
    POSITIVE LOGITS
     between
    1.61
    between
    1.48
    Between
    1.46
     Between
    1.45
     BETWEEN
    1.35
    BETWEEN
    1.31
     между
    1.27
     zwischen
    1.26
     між
    1.16
     tussen
    1.09
    Activations Density 0.141%

    No Known Activations