© 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. 254
    Prev
    Next
    INDEX
    Explanations

    components related to file handling and data structures in programming

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

    Code, files, and addresses

    np_acts-logits-general · gemini-2.0-flash

    code building blocks

    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
    initComponents
    -0.48
    
    -0.46
    )](
    -0.44
    maketitle
    -0.43
     spolup
    -0.43
    JoinTable
    -0.42
    Филь
    -0.42
     säga
    -0.42
     communism
    -0.42
    "]();
    -0.42
    POSITIVE LOGITS
     بيها
    0.84
    の中では
    0.75
     ModelExpression
    0.74
     المعيارى
    0.73
    の中でも
    0.70
    MigrationBuilder
    0.68
    BeginContext
    0.67
    migrationBuilder
    0.67
    UnsafeEnabled
    0.65
     addObject
    0.65
    Activations Density 0.234%

    No Known Activations