© 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. 14342
    Prev
    Next
    INDEX
    Explanations

    keywords related to community engagement and educational initiatives

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

    Follows first word of sentence

    np_acts-logits-general · gemini-2.0-flash

    phrases or compound 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
     zumal
    -0.31
     confronti
    -0.31
     chistes
    -0.30
     Kreise
    -0.30
     húmedo
    -0.28
     meint
    -0.28
     Ähn
    -0.28
     tecnologie
    -0.28
     fácilmente
    -0.28
     aanwezig
    -0.28
    POSITIVE LOGITS
    OGND
    0.84
    最快更新
    0.74
    GraphicsUnit
    0.72
     otomatig
    0.71
     SafeMath
    0.71
    BeginInit
    0.67
    tagHelperRunner
    0.65
     Италијани
    0.62
     noDo
    0.62
    
    0.62
    Activations Density 0.244%

    No Known Activations