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. 2492
    Prev
    Next
    INDEX
    Explanations

    references to the word "man" in various contexts, indicating a focus on male subjects or entities

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

    "Man" followed by lowercase letters

    np_acts-logits-general · gemini-2.0-flash

    man compounds and derivatives

    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
     للمعارف
    -0.63
    kmäler
    -0.53
    dération
    -0.52
    naires
    -0.52
     relev
    -0.50
    ″]
    -0.50
    GRAPHY
    -0.50
     rever
    -0.49
    CDCl
    -0.48
    jquery
    -0.48
    POSITIVE LOGITS
    tvguidetime
    0.65
     otomatig
    0.61
    intellij
    0.51
    apimachinery
    0.51
     illustrazione
    0.51
    sizeCache
    0.49
     Jungen
    0.49
     judiciaire
    0.49
    Personensuche
    0.48
     picioare
    0.48
    Activations Density 0.050%

    No Known Activations