© 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. 1160
    Prev
    Next
    INDEX
    Explanations

    temporal phrases indicating durations or time periods

    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
    +#+#
    -0.65
     }}"></
    -0.55
     lugar
    -0.51
    geführten
    -0.50
    twimg
    -0.49
    országban
    -0.48
    [];
    -0.48
     caros
    -0.48
    )}_{
    -0.47
    issau
    -0.46
    POSITIVE LOGITS
     Erişim
    0.75
    CrossRef
    0.65
    HtmlAttribute
    0.60
     Lilac
    0.59
     گذشت
    0.57
     decades
    0.57
     Silt
    0.57
     years
    0.57
     Cores
    0.57
    انيف
    0.56
    Activations Density 0.209%

    No Known Activations