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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3187
    Prev
    Next
    INDEX
    Explanations

    instances of coding structure and programming-related concepts

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

    Code snippets, interfaces, and implementations

    np_acts-logits-general · gemini-2.0-flash

    groups (n=20)

    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
    nodoc
    -0.34
     Meksiku
    -0.33
     contrary
    -0.33
    ább
    -0.32
     besides
    -0.29
    JpaRepository
    -0.28
     역
    -0.27
    Bakgrunnsstoff
    -0.26
    ENODE
    -0.26
    المكان
    -0.26
    POSITIVE LOGITS
     للاسماء
    0.62
    رشف
    0.61
     فريبيس
    0.58
     мәкал
    0.57
    Хьажоргаш
    0.54
    traditional
    0.54
    <_>
    0.53
    Bioaccumulative
    0.52
    kháu
    0.52
    transQ
    0.52
    Activations Density 0.878%

    No Known Activations