© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6139
    Prev
    Next
    INDEX
    Explanations

    terms related to funding and support for scientific research and education

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

    science and federal entities

    np_acts-logits-general · gemini-2.0-flash

    science and scientists

    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
    Geplaatst
    -0.53
    ADL
    -0.52
     @"/
    -0.48
    kmäler
    -0.47
    urlpatterns
    -0.45
     Liturgy
    -0.45
    romyal
    -0.45
    Franchise
    -0.44
    Instagram
    -0.43
     Nowy
    -0.42
    POSITIVE LOGITS
     scientists
    1.95
     scientific
    1.91
     scientist
    1.90
     science
    1.81
     Scientists
    1.72
     Scientist
    1.72
     Scientific
    1.68
    scienti
    1.66
     Science
    1.66
    Scientist
    1.63
    Activations Density 1.078%

    No Known Activations