© 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 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. 12087
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize moral dilemmas or contradictions

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

    Follows a top activating word with punctuation

    np_acts-logits-general · gemini-2.0-flash

    idioms and common sayings

    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
     kaynağından
    -0.46
    SPJ
    -0.35
    Tembelea
    -0.35
     跳转至
    -0.34
    ChildScrollView
    -0.33
    zi
    -0.33
    zingen
    -0.33
     ویکی‌آمباردا
    -0.32
    TokenNameLPAREN
    -0.32
    nha
    -0.32
    POSITIVE LOGITS
     мәкал
    0.71
    ftagPool
    0.54
     defaultstate
    0.52
     Numerade
    0.52
     AssemblyVersion
    0.52
     MainAxisSize
    0.48
    bootstrapcdn
    0.47
     sumpay
    0.47
    +:+
    0.46
    AnimationsModule
    0.46
    Activations Density 0.320%

    No Known Activations