© 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. 20-GEMMASCOPE-RES-16K
    11. 2522
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between ideas or entities in a complex context

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

    appearing after prepositions

    np_acts-logits-general · gemini-2.0-flash

    analyzed different public interactions

    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
    
    -1.07
    AndEndTag
    -0.90
     jambes
    -0.77
     يتيمه
    -0.74
    SourceChecksum
    -0.70
     surla
    -0.69
    SharedDtor
    -0.68
    Datuak
    -0.68
     sociala
    -0.68
     prochaines
    -0.67
    POSITIVE LOGITS
     contributions
    0.90
     entries
    0.86
     work
    0.72
     information
    0.70
     responses
    0.70
    contributions
    0.68
     representatives
    0.68
     interactions
    0.67
     dealings
    0.66
     efforts
    0.65
    Activations Density 1.027%

    No Known Activations