© 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 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. 15861
    Prev
    Next
    INDEX
    Explanations

    structured code snippets related to programming or mathematical operations

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

    Conversions involving "int" or integers

    np_acts-logits-general · gemini-2.0-flash

    converting to integers

    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
    はじめに
    -0.75
    GIVEREF
    -0.71
    ]='\
    -0.70
     /\.(
    -0.69
    Dziękuję
    -0.68
    saraba
    -0.68
     atof
    -0.67
    клопе
    -0.67
    WriteBarrier
    -0.66
     typelib
    -0.65
    POSITIVE LOGITS
     int
    1.11
    int
    1.11
    round
    0.87
     round
    0.85
    Int
    0.72
    Round
    0.69
     Int
    0.68
    ROUND
    0.64
     Round
    0.63
    toInt
    0.61
    Activations Density 0.229%

    No Known Activations