© 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. 3988
    Prev
    Next
    INDEX
    Explanations

    references to significant gifts and symbols of commitment in relationships

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

    after '$' in mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    stone diamond engagement ring

    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
    Демографія
    -0.58
    endforeach
    -0.58
    Viitteet
    -0.57
    JsonFormat
    -0.51
     referenties
    -0.51
     Agamemnon
    -0.49
     upo
    -0.49
    contentLoaded
    -0.48
    Permalink
    -0.45
    öy
    -0.45
    POSITIVE LOGITS
     diamond
    1.01
     ring
    0.97
     diamonds
    0.91
     Diamond
    0.87
    Diamond
    0.86
    diamond
    0.86
     Ring
    0.84
     Engagement
    0.83
     engagement
    0.82
     rings
    0.82
    Activations Density 0.388%

    No Known Activations