© 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. 15318
    Prev
    Next
    INDEX
    Explanations

    scientific and medical abbreviations or acronyms

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

    Abbreviations after definitions

    np_acts-logits-general · gemini-2.0-flash

    acronyms after separators

    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
     تانيه
    -0.64
     resourceCulture
    -0.63
    Hozzáférés
    -0.59
    UnsafeEnabled
    -0.59
    Autoritní
    -0.55
     actionMode
    -0.55
    Datuak
    -0.54
    
    -0.54
    RenderAtEndOf
    -0.54
    出版年
    -0.53
    POSITIVE LOGITS
     PSOE
    0.68
    insee
    0.67
     WQS
    0.66
     NYPD
    0.65
     MLB
    0.64
     СПб
    0.62
     fMRI
    0.62
     ggf
    0.60
     NYC
    0.60
    cshtml
    0.60
    Activations Density 1.763%

    No Known Activations