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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101936
    Prev
    Next
    INDEX
    Explanations

    phrases expressing subjective opinions or beliefs related to personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    kwür
    -0.41
     splits
    -0.41
    IVEREF
    -0.40
    fromUtf
    -0.39
     split
    -0.39
     cabinets
    -0.37
    pośred
    -0.37
    AddHtmlAttribute
    -0.36
     மே
    -0.36
     uživ
    -0.35
    POSITIVE LOGITS
    InitVars
    0.54
    Personensuche
    0.52
     nonUne
    0.50
     &___
    0.49
     resourceCulture
    0.47
     AssemblyTitle
    0.45
     հղումներ
    0.45
    Personendaten
    0.44
     disambiguazione
    0.44
     للمعارف
    0.44
    Activations Density 0.028%

    No Known Activations