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. 14561
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "the" and variations of it

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

    "The" preceding nouns or proper nouns

    np_acts-logits-general · gemini-2.0-flash

    words after "the"

    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
    RectangleBorder
    -0.84
     للاسماء
    -0.79
     pinulongan
    -0.77
     BoxDecoration
    -0.74
     CWE
    -0.74
     '\\;'
    -0.71
    клопе
    -0.70
     RIPRODUZIONE
    -0.69
    IsMutable
    -0.65
     ErrIntOverflow
    -0.65
    POSITIVE LOGITS
     new
    0.69
     project
    0.63
     program
    0.62
     programme
    0.61
     Kläger
    0.60
     company
    0.60
     second
    0.59
     first
    0.59
     film
    0.58
     other
    0.56
    Activations Density 1.602%

    No Known Activations