Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12663
    Prev
    Next
    INDEX
    Explanations

    different versions and adaptations of content, especially in the context of media and technology

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

    Preceding words of "version"

    np_acts-logits-general · gemini-2.0-flash

    modified version

    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
     חיצוניים
    -0.82
    ServletException
    -0.76
    ImageContext
    -0.74
     betweenstory
    -0.74
    HasForeignKey
    -0.71
     autorytatywna
    -0.71
    Дереккөздер
    -0.67
     Préférences
    -0.67
    ViewImports
    -0.66
    exitRule
    -0.64
    POSITIVE LOGITS
     version
    3.25
     versions
    2.88
    version
    2.61
     versión
    2.52
     Version
    2.44
     VERSION
    2.32
    Version
    2.28
     versione
    2.26
     versão
    2.26
    版本
    2.26
    Activations Density 1.014%

    No Known Activations