© 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. 85165
    Prev
    Next
    INDEX
    Explanations

    language and phrases that express comparison, value, or satisfaction

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

    judging quality or state

    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
     للاسماء
    -0.65
     otomatig
    -0.58
     <<<<<<<<<<<<<<
    -0.57
     GenerationType
    -0.56
     EconPapers
    -0.55
    enumi
    -0.51
    OGND
    -0.50
     ویکی‌پدی
    -0.50
     CreateTagHelper
    -0.48
     surla
    -0.47
    POSITIVE LOGITS
     romántico
    0.33
    齑
    0.31
     literaria
    0.31
     industriale
    0.31
     épreuves
    0.31
     ✭✭
    0.31
    Bik
    0.30
     Dingen
    0.30
     perkara
    0.30
     garansi
    0.30
    Activations Density 0.154%

    No Known Activations