Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 7471
    Prev
    Next
    INDEX
    Explanations

    instances of the word "since."

    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
     Leah
    -0.85
     Shari
    -0.71
    Leah
    -0.69
     Waray
    -0.67
     Leroy
    -0.66
     Rebekah
    -0.65
     Wir
    -0.61
     Deadpool
    -0.60
     Livermore
    -0.60
    abestanden
    -0.60
    POSITIVE LOGITS
    since
    2.02
     since
    1.96
     SINCE
    1.95
     Since
    1.70
    Since
    1.69
    Seit
    1.38
     fince
    1.34
     Depuis
    1.32
    depuis
    1.25
     Seit
    1.23
    Activations Density 0.091%

    No Known Activations