© 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. 24-GEMMASCOPE-RES-16K
    11. 14654
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal processes and terms

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

    "...until" or words containing "un" prefixes

    np_acts-logits-general · gemini-2.0-flash

    delayed until

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Till
    -1.11
     Till
    -1.08
    till
    -0.99
     TILL
    -0.95
     till
    -0.92
    BEFORE
    -0.72
     Jusqu
    -0.69
     فريبيس
    -0.69
     Before
    -0.69
    Before
    -0.67
    POSITIVE LOGITS
     unt
    0.77
     unit
    0.75
    unit
    0.72
    Unit
    0.69
     Unit
    0.67
     unul
    0.63
     util
    0.63
     unil
    0.62
     UNIT
    0.62
    UNIT
    0.58
    Activations Density 0.114%

    No Known Activations