© 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. 25-GEMMASCOPE-RES-16K
    11. 463
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and function definitions in code snippets

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

    programming-related terms and syntax within a code context

    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
     creation
    -1.23
    creation
    -1.19
     conversion
    -1.13
     restoration
    -1.11
    conversion
    -1.11
    removal
    -1.10
     Creation
    -1.08
     removal
    -1.07
    Creation
    -1.06
     cancellation
    -1.05
    POSITIVE LOGITS
     planète
    0.67
     collide
    0.58
     innovate
    0.58
    locate
    0.57
    reathe
    0.57
     certify
    0.57
     nominate
    0.56
     calibrate
    0.55
     authenticate
    0.55
     simulate
    0.54
    Activations Density 0.761%

    No Known Activations