© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 13455
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms commonly used in scientific terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.58
    glBindBuffer
    -0.56
     nahilalakip
    -0.55
    Ծանոթ
    -0.53
    ndice
    -0.50
    fjspx
    -0.50
     Serikat
    -0.49
    KURZBESCHREIBUNG
    -0.49
    はじめに
    -0.48
    Tazama
    -0.48
    POSITIVE LOGITS
     ['./
    0.57
    YSTEM
    0.45
    ंटर
    0.45
    sac
    0.45
    τευ
    0.44
    getRuntime
    0.43
    Geplaatst
    0.43
     Eliot
    0.42
    herin
    0.42
    phere
    0.42
    Activations Density 0.309%

    No Known Activations