© 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. 8996
    Prev
    Next
    INDEX
    Explanations

    mathematical representations and equations involving exponential functions

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

    LaTeX math formulas

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation

    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
    HomeAsUpEnabled
    -0.43
     mémoire
    -0.41
     terza
    -0.40
    sság
    -0.39
     quitt
    -0.39
     tendre
    -0.39
     recher
    -0.39
    rau
    -0.36
    եր
    -0.36
     Valores
    -0.35
    POSITIVE LOGITS
     lenker
    1.04
     EconPapers
    0.96
     Réponses
    0.96
    postsleuth
    0.89
    FormTagHelper
    0.89
    ImageContext
    0.89
    aarrggbb
    0.87
     nahilalakip
    0.87
     يتيمه
    0.85
     Wikimedijinoj
    0.85
    Activations Density 0.840%

    No Known Activations