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. 6698
    Prev
    Next
    INDEX
    Explanations

    references to specific dates and numerical data within the text

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

    Tokens preceding months

    np_acts-logits-general · gemini-2.0-flash

    months following dates

    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
    Geplaatst
    -0.98
    AddTagHelper
    -0.96
     pinulongan
    -0.94
    tvguidetime
    -0.91
    tagHelperRunner
    -0.89
    
    -0.89
     kasarigan
    -0.87
    IntoConstraints
    -0.85
     Monfieur
    -0.84
    المشاركات
    -0.84
    POSITIVE LOGITS
    cuss
    0.56
    <unused61>
    0.56
    <unused62>
    0.54
    <unused63>
    0.53
    <unused60>
    0.53
     ha
    0.51
     unknown
    0.48
    toBeTruthy
    0.46
    hena
    0.46
     T
    0.46
    Activations Density 0.806%

    No Known Activations