© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 11284
    Prev
    Next
    INDEX
    Explanations

    phrases related to modular components and their assembly in a system

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

    modular components

    np_acts-logits-general · gemini-2.0-flash

    modules and subunits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kursi
    -0.44
     wipers
    -0.44
    kian
    -0.43
     Under
    -0.43
     CreateTagHelper
    -0.43
     Commission
    -0.42
    kain
    -0.42
     begy
    -0.42
    lain
    -0.41
    eniging
    -0.41
    POSITIVE LOGITS
     modules
    1.08
     module
    0.99
     Modules
    0.99
     segments
    0.90
     مشين
    0.87
     Module
    0.87
     blocks
    0.84
     módulos
    0.82
     sections
    0.82
    模块
    0.80
    Activations Density 1.021%

    No Known Activations