© 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-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 2827
    Prev
    Next
    INDEX
    Explanations

    questions starting with "Did" or variations of the word "did."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     does
    -0.30
    parece
    -0.27
     sometimes
    -0.27
     putus
    -0.26
    AnimationsModule
    -0.25
     comes
    -0.25
     бывает
    -0.24
     diejenigen
    -0.24
     happens
    -0.24
    ASES
    -0.24
    POSITIVE LOGITS
    did
    1.01
     Did
    0.96
    Did
    0.93
    DID
    0.88
     DID
    0.86
    sizeCache
    0.85
    didSet
    0.78
    Personendaten
    0.73
     did
    0.72
    rungsseite
    0.72
    Activations Density 0.146%

    No Known Activations