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

    Neuronpedia

    Jacobian LensNEW
    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. 14842
    Prev
    Next
    INDEX
    Explanations

    phrases related to marriage and romantic partnerships

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

    Association or correlation between variables

    np_acts-logits-general · gemini-2.0-flash

    is associated with

    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
    isiaj
    -0.58
    ulose
    -0.55
     esimer
    -0.55
    طبيق
    -0.53
    ISupport
    -0.53
    etheless
    -0.53
    phane
    -0.52
    ❸
    -0.52
    NetworkInfo
    -0.52
     gdyby
    -0.52
    POSITIVE LOGITS
     correlated
    0.85
     correlates
    0.84
     correlate
    0.80
     association
    0.73
     linked
    0.71
    correlated
    0.70
     associations
    0.69
     correlation
    0.66
     correlations
    0.66
     associate
    0.62
    Activations Density 1.244%

    No Known Activations