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. 2232
    Prev
    Next
    INDEX
    Explanations

    references to actions, conditions, or attributes related to products and their specifications

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

    after "be" or "being"

    np_acts-logits-general · gemini-2.0-flash

    classifications or states

    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
     intermédiaire
    -0.65
     illustrazione
    -0.63
     sufficiente
    -0.63
     Lordships
    -0.62
     suprême
    -0.62
     alternativo
    -0.61
     rând
    -0.59
     quelcon
    -0.59
     normaux
    -0.59
     titolata
    -0.59
    POSITIVE LOGITS
     vegetarian
    0.79
     non
    0.78
     female
    0.77
     male
    0.73
    UnusedPrivate
    0.71
     unisex
    0.69
     vegan
    0.67
     bilingual
    0.66
     FEMALE
    0.64
     Vegetarian
    0.63
    Activations Density 0.883%

    No Known Activations