© 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 EvalsExportsinterp-engineNEWAPI 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. 16258
    Prev
    Next
    INDEX
    Explanations

    references to programming languages and related technical terms

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

    "Flash" or "flash"

    np_acts-logits-general · gemini-2.0-flash

    FlashOS

    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
     AssemblyCulture
    -0.97
    SharedCtor
    -0.72
     resourceCulture
    -0.72
    RegressionTest
    -0.69
    IntoConstraints
    -0.68
     heapq
    -0.66
    #+#
    -0.65
    Sucesor
    -0.64
    ⓧ
    -0.63
     LEYENDO
    -0.63
    POSITIVE LOGITS
     Flash
    1.13
     flash
    0.99
    Flash
    0.97
    flash
    0.88
     Adobe
    0.82
     FLASH
    0.79
     Javascript
    0.76
     JavaScript
    0.72
    FLASH
    0.71
    JavaScript
    0.71
    Activations Density 0.331%

    No Known Activations