© 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. 123974
    Prev
    Next
    INDEX
    Explanations

    phrases that involve addressing the reader directly with possibilities or uncertainties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     zostać
    -0.39
    なのでしょう
    -0.38
     Empfehlungen
    -0.37
     Existenz
    -0.36
    wußt
    -0.35
     Grenze
    -0.34
     Wege
    -0.34
     quedarse
    -0.33
     Lösungen
    -0.33
     schweren
    -0.33
    POSITIVE LOGITS
    BeginContext
    0.67
    UnknownFieldSet
    0.60
    GOTREF
    0.59
    تقاوى
    0.58
     تانيه
    0.56
     EconPapers
    0.56
    ultati
    0.53
     esternos
    0.53
     Italijanski
    0.52
    nesium
    0.51
    Activations Density 0.021%

    No Known Activations