© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8538
    Prev
    Next
    INDEX
    Explanations

    various verb forms related to arrival events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ++)
    -0.69
    </i>
    -0.64
     K
    -0.63
    getSubject
    -0.61
     Eber
    -0.61
     Kitts
    -0.59
     C
    -0.58
    setString
    -0.57
     k
    -0.57
     ello
    -0.56
    POSITIVE LOGITS
     arrivals
    1.61
    arrived
    1.61
     Arrival
    1.60
     arrival
    1.60
     Arri
    1.58
     arrived
    1.54
     arrives
    1.53
     Arrivals
    1.49
    Arri
    1.48
     Arrive
    1.48
    Activations Density 0.058%

    No Known Activations