© 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. 6942
    Prev
    Next
    INDEX
    Explanations

    data structure definitions and their associated properties

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

    Follows colons in code

    np_acts-logits-general · gemini-2.0-flash

    kotlin, swift, java, rust function signatures

    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
    ViewFeatures
    -0.61
     just
    -0.53
     rel
    -0.51
     resultCode
    -0.50
    yid
    -0.49
     pre
    -0.48
     invokingState
    -0.48
    Гео
    -0.48
    endpush
    -0.46
    توان
    -0.46
    POSITIVE LOGITS
    CloseOperation
    1.10
    Personensuche
    0.73
     насељу
    0.65
    tableFuture
    0.63
    RegressionTest
    0.63
    ">//
    0.62
    ThroughAttribute
    0.61
     Wikimedijinoj
    0.60
    utives
    0.60
    GEBURTS
    0.60
    Activations Density 0.052%

    No Known Activations