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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 456
    Prev
    Next
    INDEX
    Explanations

    phrases and words associated with customer service and satisfaction

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

    "Your" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    your followed by a noun

    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
     nearly
    -0.40
     strangely
    -0.38
    Nearly
    -0.37
    Тарихы
    -0.37
     similarly
    -0.36
     Nearly
    -0.36
    nearly
    -0.36
     unfortunately
    -0.35
     scre
    -0.35
     weirdly
    -0.34
    POSITIVE LOGITS
     pinulongan
    0.65
     pleaſure
    0.57
     neceſſ
    0.54
     oprot
    0.52
    ScopeManager
    0.51
    ModelSerializer
    0.50
     Anſ
    0.48
     ligiloj
    0.48
     reaſon
    0.48
     ſhall
    0.48
    Activations Density 0.093%

    No Known Activations