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. 3229
    Prev
    Next
    INDEX
    Explanations

    financial figures and monetary values in the text

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

    Dollar amounts

    np_acts-logits-general · gemini-2.0-flash

    millions and billions

    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
     eventdata
    -0.56
     Thread
    -0.47
     thousands
    -0.42
    orice
    -0.41
     thousand
    -0.40
    gefahr
    -0.40
     Pane
    -0.40
     cref
    -0.40
    Thread
    -0.40
     pane
    -0.39
    POSITIVE LOGITS
     billion
    0.94
     billions
    0.87
     millions
    0.83
     milliards
    0.83
    SequentialGroup
    0.82
     Billion
    0.80
    millions
    0.80
    billion
    0.80
     milliard
    0.79
    verwijspagina
    0.78
    Activations Density 0.202%

    No Known Activations