© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 3402
    Prev
    Next
    INDEX
    Explanations

    references to direct assistance or support involving personal pronouns

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

    me, you, them, us

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     Grenz
    -0.31
     تت
    -0.28
     muut
    -0.27
     kommet
    -0.27
     faibles
    -0.27
     kijang
    -0.26
     modalidad
    -0.26
     fl
    -0.25
     ч
    -0.25
    czną
    -0.25
    POSITIVE LOGITS
    abetes
    0.80
    +#+#
    0.77
    SharedDtor
    0.73
     Савезне
    0.73
     oprot
    0.71
    niſſe
    0.69
    tagHelperRunner
    0.68
     Италијани
    0.67
     EconPapers
    0.67
    EndContext
    0.67
    Activations Density 0.016%

    No Known Activations