Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3526
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to renting and leasing properties

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

    Terms and conditions of renting

    np_acts-logits-general · gemini-2.0-flash

    rental and lease agreements

    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
     pazi
    -0.49
     faccia
    -0.49
     Scherer
    -0.48
     שוליים
    -0.47
     cioccolato
    -0.46
    Шо
    -0.46
     kaik
    -0.45
     ferdig
    -0.45
     Pohl
    -0.44
     tocando
    -0.42
    POSITIVE LOGITS
     rental
    0.94
     rent
    0.93
    Rent
    0.87
     Rent
    0.85
     Rental
    0.84
     rentals
    0.82
     rented
    0.82
     renting
    0.81
     Lease
    0.79
     lease
    0.78
    Activations Density 0.225%

    No Known Activations