© 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. 4-GEMMASCOPE-RES-16K
    11. 15435
    Prev
    Next
    INDEX
    Explanations

    references to academic resources, specifically Google Scholar citations and mentions of SOAP libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prefix
    -0.52
     stanovnika
    -0.50
    pinMode
    -0.47
    Открыть
    -0.46
    تعداد
    -0.45
    btnNew
    -0.44
    webb
    -0.44
    ".$_
    -0.43
    ALIAN
    -0.42
    Interfaces
    -0.42
    POSITIVE LOGITS
     Scholar
    1.28
    Scholar
    1.13
    ValueStyle
    1.11
     Scholars
    0.98
     ComVisible
    0.98
    Scholars
    0.92
     scholar
    0.92
    scholar
    0.91
    //
    0.90
    EndContext
    0.88
    Activations Density 0.013%

    No Known Activations