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. 20-GEMMASCOPE-RES-16K
    6. 10322
    Prev
    Next
    INDEX
    Explanations

    expressions related to emotional reflection and loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Before personal pronouns or nouns

    np_acts-logits-general · gemini-2.0-flash

    Millennia, fallen kingdoms, warriors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     basically
    -0.81
     Basically
    -0.77
    Basically
    -0.74
    basically
    -0.72
     stuff
    -0.68
     dude
    -0.66
     pretty
    -0.65
     guy
    -0.64
     FYI
    -0.62
     dudes
    -0.61
    POSITIVE LOGITS
     déchir
    0.77
     découver
    0.77
     automatiques
    0.70
     shall
    0.69
     näin
    0.68
     humains
    0.67
     thine
    0.67
     sonno
    0.66
     sogni
    0.66
     geomé
    0.66
    Activations Density 0.684%

    No Known Activations