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. 4939
    Prev
    Next
    INDEX
    Explanations

    frequent conjunctions and determiners in the context of gene research and technical discussions

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

    Possessive pronouns followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    possessive or related association

    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
    :✨
    -0.62
     nemlig
    -0.52
     löytyy
    -0.52
    Hentet
    -0.51
    /***/
    -0.45
     namelijk
    -0.45
     nämlich
    -0.45
    Życiorys
    -0.43
     مُعرِّف
    -0.42
     endroits
    -0.42
    POSITIVE LOGITS
     associated
    1.91
     related
    1.83
     accompanying
    1.68
     its
    1.67
     corresponding
    1.64
    associated
    1.58
    corresponding
    1.52
     Related
    1.48
    related
    1.47
     RELATED
    1.38
    Activations Density 0.899%

    No Known Activations