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. 10976
    Prev
    Next
    INDEX
    Explanations

    monetary values and financial figures

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

    Dollar amounts with comma separators

    np_acts-logits-general · gemini-2.0-flash

    numbers with commas

    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
    -0.67
     indeb
    -0.53
    Nuorodos
    -0.51
     Ever
    -0.51
    ATURE
    -0.51
    tonsoft
    -0.47
    SpringBootTest
    -0.46
     годах
    -0.46
     utafitiHapana
    -0.45
    <bos>
    -0.44
    POSITIVE LOGITS
    Région
    0.64
     lagoons
    0.59
    ribune
    0.58
    ContentAsync
    0.57
     Citroën
    0.55
    berfläche
    0.54
    Portail
    0.53
    idemiology
    0.53
     velour
    0.53
     grease
    0.53
    Activations Density 0.192%

    No Known Activations