© 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. 9211
    Prev
    Next
    INDEX
    Explanations

    references to JavaScript libraries and frameworks

    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
    OGND
    -0.58
     Zweig
    -0.56
    ItemLayout
    -0.54
    uxxxx
    -0.53
    EndGlobalSection
    -0.52
    Hochspringen
    -0.50
     Mandal
    -0.49
     Petra
    -0.49
    Wolfe
    -0.49
    hbase
    -0.48
    POSITIVE LOGITS
     scripts
    1.13
     script
    1.12
     js
    1.06
     Script
    1.02
    script
    1.02
     Scripts
    1.02
    Scripts
    1.01
     SCRIPT
    1.00
    Script
    1.00
     JavaScript
    1.00
    Activations Density 0.546%

    No Known Activations