© 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. 41
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terms related to distributions and statistical functions

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

    ".math" after a dot in a filepath

    np_acts-logits-general · gemini-2.0-flash

    apache commons math

    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
     Roskov
    -0.75
    SourceChecksum
    -0.74
     للاسماء
    -0.73
    verifyException
    -0.68
    ///</
    -0.66
    InjectAttribute
    -0.65
     оригіналу
    -0.62
     Erişim
    -0.61
    mybatisplus
    -0.60
    errHandler
    -0.60
    POSITIVE LOGITS
     Савезне
    0.73
     الرياضيه
    0.52
     Qar
    0.50
     COE
    0.49
     OPC
    0.49
     webb
    0.49
     OnTrigger
    0.48
     Normdatei
    0.48
     NIOS
    0.48
    וויק
    0.47
    Activations Density 0.026%

    No Known Activations