© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15040
    Prev
    Next
    INDEX
    Explanations

    instances of leaving or departing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tellung
    -0.52
    adre
    -0.51
    mlen
    -0.49
     createState
    -0.49
    ngilizce
    -0.49
    getConfiguration
    -0.48
    Inclu
    -0.47
    ronique
    -0.45
     Inclu
    -0.44
     Omb
    -0.44
    POSITIVE LOGITS
     departure
    1.20
     Departure
    1.04
     leaving
    1.04
     exit
    1.04
     departing
    1.03
    Departure
    1.00
     departures
    1.00
    departure
    0.99
     depart
    0.98
    exit
    0.94
    Activations Density 0.289%

    No Known Activations