© 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. 14432
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong emotions or personal reactions

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

    End of turn markers

    np_acts-logits-general · gemini-2.0-flash

    QMetaType, UrlResolution, Q

    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
    脚注の使い方
    -0.59
     kasarigan
    -0.59
    lexia
    -0.50
    Hauptartikel
    -0.49
     $_(
    -0.48
    Personensuche
    -0.47
     dealers
    -0.47
    lims
    -0.47
     الحره
    -0.47
     Dealers
    -0.46
    POSITIVE LOGITS
     '\\;'
    0.36
    QMetaType
    0.34
    AsUp
    0.34
    intios
    0.29
    ⋯
    0.29
    UrlResolution
    0.28
    UrlEncoded
    0.28
    ting
    0.28
    LookAnd
    0.28
    WriteAttribute
    0.27
    Activations Density 1.021%

    No Known Activations