© 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. 136
    Prev
    Next
    INDEX
    Explanations

    specific technical or procedural terms related to various fields such as computing, culture, and science

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

    after specific nouns

    np_acts-logits-general · gemini-2.0-flash

    specific technical and domain terms

    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
     للمعارف
    -0.55
    Tembelea
    -0.44
    
    -0.43
     мәкал
    -0.39
    tagHelperRunner
    -0.35
    
    -0.35
     AssemblyCompany
    -0.34
    aktif
    -0.34
     Normdatei
    -0.33
    enumii
    -0.33
    POSITIVE LOGITS
    ArrowToggle
    0.64
    RegressionTest
    0.46
    🫲
    0.45
    postsleuth
    0.44
    ;';
    0.44
    felves
    0.43
     дописавши
    0.43
    featureID
    0.43
    MessageOf
    0.42
     itself
    0.41
    Activations Density 1.725%

    No Known Activations