© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13338
    Prev
    Next
    INDEX
    Explanations

    words related to programming or software-related language components

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

    Programming languages and related terms

    np_acts-logits-general · gemini-2.0-flash

    appsensor, elle, FreeHEP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     createSprite
    -0.39
    erschutz
    -0.36
    équi
    -0.35
     kullanılan
    -0.34
    kembangan
    -0.34
     before
    -0.33
     gober
    -0.33
     interesan
    -0.33
     when
    -0.33
     conozco
    -0.33
    POSITIVE LOGITS
    tagHelperRunner
    0.92
     CreateTagHelper
    0.90
    expandindo
    0.83
     مشين
    0.77
     MainAxisSize
    0.77
     queſta
    0.73
    GEBURTSDATUM
    0.72
     protoimpl
    0.71
     surla
    0.69
    Personensuche
    0.69
    Activations Density 0.170%

    No Known Activations