© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13763
    Prev
    Next
    INDEX
    Explanations

    code syntax and programming constructs related to file operations and memory management

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

    Code, file paths, or file system metadata

    np_acts-logits-general · gemini-2.0-flash

    root, Root, ROOT, racine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saks
    -0.54
    CppMethod
    -0.54
    Subclass
    -0.52
    SubMenu
    -0.48
    Données
    -0.48
    RestClient
    -0.47
    lemen
    -0.47
     đời
    -0.46
     Penrose
    -0.46
    Tembelea
    -0.46
    POSITIVE LOGITS
    InitVars
    0.77
     root
    0.76
     Root
    0.72
    Root
    0.71
    IContainer
    0.65
    root
    0.64
    ROOT
    0.62
     racine
    0.61
     MotionEvent
    0.60
    artifactId
    0.58
    Activations Density 0.483%

    No Known Activations