© 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. 39-GEMMASCOPE-RES-16K
    11. 868
    Prev
    Next
    INDEX
    Explanations

    references to timeframes and the frequency of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرخصة
    -0.38
     désolés
    -0.37
    səhifə
    -0.36
    исленность
    -0.35
     CanadaChoose
    -0.33
    MessageTagHelper
    -0.33
     تانيه
    -0.31
     tege
    -0.31
    sizeCache
    -0.31
    kegaard
    -0.31
    POSITIVE LOGITS
     years
    2.48
     months
    1.91
    years
    1.80
     weeks
    1.78
     YEARS
    1.71
     Years
    1.63
    Years
    1.63
     decades
    1.59
     años
    1.53
     days
    1.51
    Activations Density 0.636%

    No Known Activations