© 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. 1753
    Prev
    Next
    INDEX
    Explanations

    syntax-related elements and declarations in programming code

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

    Variable types (int, char, boolean, string)

    np_acts-logits-general · gemini-2.0-flash

    c/c++ data types and pointers

    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
     automatiques
    -0.32
     commerciales
    -0.31
    pēc
    -0.29
     choisissez
    -0.29
     senaste
    -0.28
    autoreleasepool
    -0.28
     convertirse
    -0.28
     vaikka
    -0.28
    toBeTruthy
    -0.28
     pueda
    -0.27
    POSITIVE LOGITS
     للاسماء
    0.98
     propOrder
    0.82
     الحره
    0.69
    الحياه
    0.67
    hoeddwyd
    0.65
     дописавши
    0.65
    MethodManager
    0.63
    findpost
    0.63
     оригіналу
    0.61
    ########.
    0.60
    Activations Density 0.092%

    No Known Activations