© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 8595
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "last" and variations in the context of time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Réponses
    -0.96
    Portale
    -0.85
     }</
    -0.83
     noqa
    -0.82
     AppColors
    -0.77
    endous
    -0.76
    IPCC
    -0.75
     TestBed
    -0.75
    MemoryWarning
    -0.74
     saurait
    -0.74
    POSITIVE LOGITS
     year
    0.68
     week
    0.67
     last
    0.51
     Last
    0.49
    expandindo
    0.47
     weekend
    0.47
    last
    0.47
     night
    0.45
     LAST
    0.45
    Last
    0.44
    Activations Density 0.043%

    No Known Activations