© 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. 4-GEMMASCOPE-RES-16K
    6. 12914
    Prev
    Next
    INDEX
    Explanations

    the word "since" and its variations, indicating temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enllaços
    -0.76
    DoubleQuotes
    -0.61
     bait
    -0.59
    UNIDENTIFIED
    -0.59
     Mehdi
    -0.58
    Bait
    -0.57
     Shahid
    -0.55
    ر
    -0.55
    Ethereum
    -0.54
    AnchorStyles
    -0.54
    POSITIVE LOGITS
     since
    1.73
    since
    1.70
     Since
    1.70
    Since
    1.69
     SINCE
    1.61
     puisque
    1.14
    скольку
    1.12
     fince
    0.96
    Depuis
    0.95
     Depuis
    0.95
    Activations Density 0.095%

    No Known Activations