© 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. 5-GEMMASCOPE-RES-16K
    11. 8013
    Prev
    Next
    INDEX
    Explanations

    specific temporal references, particularly months and halves of years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     them
    -0.54
     ha
    -0.48
    Tracce
    -0.47
    arakhand
    -0.47
     Insee
    -0.46
    pina
    -0.46
     only
    -0.46
    oldi
    -0.46
    ubakar
    -0.45
     standing
    -0.45
    POSITIVE LOGITS
     mediados
    0.88
     comienzos
    0.76
     początku
    0.74
    raisemb
    0.73
     inicios
    0.70
     early
    0.70
     late
    0.70
    Late
    0.69
    throughout
    0.68
    early
    0.67
    Activations Density 0.209%

    No Known Activations