© 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. 12201
    Prev
    Next
    INDEX
    Explanations

    coding constructs and structures in programming language syntax

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

    Code-related terms, often after "if"

    np_acts-logits-general · gemini-2.0-flash

    conditional code constructs

    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
    EndInit
    -0.44
     zudem
    -0.35
     respectively
    -0.32
     aprendiz
    -0.31
     moreover
    -0.30
     colleagues
    -0.30
    cinta
    -0.30
     accordingly
    -0.29
    chra
    -0.29
     displays
    -0.28
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.54
     snippetHide
    0.53
    Geplaatst
    0.52
    Revenir
    0.52
    عرِّف
    0.51
    Життєпис
    0.51
     ujednoznacz
    0.50
    FIX
    0.50
    sizeCache
    0.50
    Демографія
    0.50
    Activations Density 0.227%

    No Known Activations