© 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. 125
    Prev
    Next
    INDEX
    Explanations

    terms related to electronic or digital components and their functions

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

    Signals from sensors or encoders

    np_acts-logits-general · gemini-2.0-flash

    signals, output, and data flow

    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
    RegressionTest
    -0.88
    قایناق‌لار
    -0.87
     nahilalakip
    -0.78
     Normdatei
    -0.73
     BoxFit
    -0.72
    tagHelperRunner
    -0.70
    SharedCtor
    -0.70
    Демографія
    -0.68
     تضيفلها
    -0.68
    PerformLayout
    -0.66
    POSITIVE LOGITS
     output
    1.16
     signals
    1.13
     signal
    1.07
     input
    0.99
    output
    0.93
     inputs
    0.93
     feed
    0.93
     outputs
    0.92
     incoming
    0.89
    signals
    0.85
    Activations Density 0.902%

    No Known Activations