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. 13768
    Prev
    Next
    INDEX
    Explanations

    instances of the word "there."

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

    "There" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    there is

    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
    脚注の使い方
    -0.87
    ьаж
    -0.70
    +#+#
    -0.68
    PreferredItem
    -0.68
     SafeMath
    -0.64
    verifyException
    -0.64
    KommentareTeilen
    -0.60
     onAnimation
    -0.60
     wikipagina
    -0.60
    fjspx
    -0.58
    POSITIVE LOGITS
     are
    0.79
     is
    0.75
     Waray
    0.68
     needs
    0.65
     has
    0.61
     was
    0.60
     habido
    0.59
     will
    0.59
     isn
    0.58
     clearly
    0.57
    Activations Density 0.090%

    No Known Activations