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. 2709
    Prev
    Next
    INDEX
    Explanations

    closing tags in HTML markup

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

    HTML div tags

    np_acts-logits-general · gemini-2.0-flash

    html div

    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
    GHIJKLM
    -0.50
     patata
    -0.48
    ument
    -0.45
     Stre
    -0.45
    andam
    -0.45
     Oldenburg
    -0.44
    istes
    -0.43
    nlm
    -0.43
    ế
    -0.43
     Ramesh
    -0.43
    POSITIVE LOGITS
    div
    1.55
     div
    1.23
    Div
    1.21
    DIV
    1.15
     DIV
    1.13
     Div
    1.09
    diva
    0.93
     divisions
    0.90
     divinity
    0.89
     divi
    0.89
    Activations Density 0.038%

    No Known Activations