© 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. 5-GEMMASCOPE-RES-16K
    11. 36
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "basis" in legal or contractual contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PREF
    -0.81
    ANNED
    -0.74
     Sleepy
    -0.71
    WithMany
    -0.71
    zepine
    -0.69
     Supremo
    -0.68
    owulf
    -0.68
    riezmann
    -0.68
     Dumont
    -0.68
     otomatig
    -0.68
    POSITIVE LOGITS
     Basis
    1.80
    basis
    1.79
     BASIS
    1.78
     basis
    1.76
    Basis
    1.72
     bases
    0.82
     Bases
    0.79
     wijze
    0.77
     occasion
    0.76
     أساس
    0.74
    Activations Density 0.127%

    No Known Activations