© 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. 15-GEMMASCOPE-RES-16K
    6. 1107
    Prev
    Next
    INDEX
    Explanations

    characteristics related to ease of use and accessibility in various methods or tools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ErrIntOverflow
    -0.87
     للاسماء
    -0.72
    thâu
    -0.64
     Италијани
    -0.62
    PerformLayout
    -0.62
    verwijspagina
    -0.62
     يتيمه
    -0.60
    protoimpl
    -0.60
     utafiti
    -0.59
     Савезне
    -0.59
    POSITIVE LOGITS
     easy
    1.41
    easy
    1.22
     Easy
    1.17
    Easy
    1.11
     EASY
    1.08
     inexpensive
    1.08
     mudah
    1.04
     simple
    0.97
     easily
    0.96
     easier
    0.93
    Activations Density 0.539%

    No Known Activations