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

    Neuronpedia

    Jacobian LensNEW
    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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15021
    Prev
    Next
    INDEX
    Explanations

    mentions of arrival and related phrases

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

    Tokens related to arriving

    np_acts-logits-general · gemini-2.0-flash

    arrival and timing

    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
    bladet
    -0.45
    Pascal
    -0.44
     Spinoza
    -0.44
    ServiceTest
    -0.43
    3
    -0.43
     Cowper
    -0.43
    engeti
    -0.43
     Svensk
    -0.43
    weakSelf
    -0.43
    black
    -0.43
    POSITIVE LOGITS
     arrival
    1.20
     Arrival
    1.19
    Arrival
    1.05
     arrive
    1.01
    arrival
    0.98
     arrived
    0.98
     arriving
    0.97
     Arrive
    0.96
     arrivals
    0.96
     arrives
    0.95
    Activations Density 0.065%

    No Known Activations