© 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. 10109
    Prev
    Next
    INDEX
    Explanations

    coding-related syntax and structural elements

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

    Code snippets, especially brackets and semicolons

    np_acts-logits-general · gemini-2.0-flash

    closing code blocks

    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
     ujednoznacz
    -0.73
     nonUne
    -0.68
    hoea
    -0.63
     InputDecoration
    -0.62
     geſch
    -0.61
     gynhyrchwyd
    -0.61
    romyalgia
    -0.60
    UrlResolution
    -0.60
    ſelben
    -0.59
     ſei
    -0.59
    POSITIVE LOGITS
     yet
    0.35
     ActionListener
    0.30
     lief
    0.29
    做
    0.29
     paik
    0.29
     Maj
    0.27
     connaissance
    0.26
     therefore
    0.26
     conferencia
    0.26
     after
    0.25
    Activations Density 0.089%

    No Known Activations