© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9777
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ongoing action or involvement

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

    "are" followed by a verb ending in "-ing"

    np_acts-logits-general · gemini-2.0-flash

    are being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sebuah
    -0.57
    ViewImports
    -0.57
     oscu
    -0.56
     själv
    -0.55
     nuages
    -0.53
     popolari
    -0.52
    torem
    -0.50
    wertes
    -0.50
    zenta
    -0.49
     U
    -0.48
    POSITIVE LOGITS
     themselves
    1.34
    themselves
    1.14
     flock
    1.01
     nahilalakip
    0.88
     themſelves
    0.85
     JpaRepository
    0.81
    纷纷
    0.81
    цездатний
    0.80
    Their
    0.79
     flocked
    0.78
    Activations Density 0.351%

    No Known Activations