© 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. 20-GEMMASCOPE-RES-16K
    6. 5829
    Prev
    Next
    INDEX
    Explanations

    terms related to health, environment, and legal frameworks

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

    ending in "-al", "-ive", or "-ic"

    np_acts-logits-general · gemini-2.0-flash

    functional and conceptual domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     complètes
    -0.60
     singola
    -0.59
     dignité
    -0.57
     gouvernements
    -0.55
     refusé
    -0.55
     épais
    -0.55
     totalité
    -0.53
     corriger
    -0.52
    tagHelperRunner
    -0.52
     abandonné
    -0.52
    POSITIVE LOGITS
     considerations
    1.27
     aspects
    1.25
     implications
    1.12
     issues
    1.11
     aspect
    0.99
     factors
    0.94
     requirements
    0.94
    aspects
    0.92
     concerns
    0.90
     matters
    0.88
    Activations Density 0.948%

    No Known Activations