© 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. 1465
    Prev
    Next
    INDEX
    Explanations

    descriptive attributes and features of accommodations and vacation rentals

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

    Accommodation rentals and lodging

    np_acts-logits-general · gemini-2.0-flash

    accommodation and rentals

    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
     autorytatywna
    -0.57
     nahilalakip
    -0.47
     Versch
    -0.44
     DIAG
    -0.40
     bağlantılar
    -0.40
     diagnostic
    -0.40
    pneu
    -0.39
    Elton
    -0.39
    PRNewswire
    -0.39
    default
    -0.38
    POSITIVE LOGITS
    findpost
    0.64
    sizeCache
    0.56
     препратки
    0.49
     guesthouse
    0.48
     farmhouse
    0.48
     informée
    0.47
     renters
    0.45
     rentals
    0.44
    chyma
    0.43
     Photocase
    0.43
    Activations Density 0.028%

    No Known Activations