© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 777
    Prev
    Next
    INDEX
    Explanations

    terms related to expertise and expert opinions

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

    "expert" or "experts"

    np_acts-logits-general · gemini-2.0-flash

    expert advice or recommendations

    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
    Fußball
    -0.51
     MotionEvent
    -0.49
     Clothes
    -0.46
     Snapchat
    -0.45
    NavigationBar
    -0.45
     Wallpapers
    -0.45
     Sinus
    -0.44
    Facebook
    -0.44
     صفحۀ
    -0.43
     Facebook
    -0.43
    POSITIVE LOGITS
     Expert
    1.30
     expert
    1.29
    Expert
    1.25
    expert
    1.24
     experts
    1.20
     EXPERT
    1.17
     Experts
    1.16
    experts
    1.14
    Experts
    1.08
     experto
    1.07
    Activations Density 0.071%

    No Known Activations