© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 3062
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "may" and its contextual implications regarding possibility

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

    "May" followed by a negation

    np_acts-logits-general · gemini-2.0-flash

    expressing uncertainty or possibility

    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
    RTEX
    -0.93
     lenker
    -0.77
    تقاوى
    -0.74
    AndEndTag
    -0.70
     gynhyrchwyd
    -0.69
    DoubleQuotes
    -0.68
     numberWith
    -0.64
    UserScript
    -0.63
     suivants
    -0.62
     majeurs
    -0.60
    POSITIVE LOGITS
     well
    1.30
     very
    0.91
    well
    0.87
     even
    0.86
     Well
    0.82
    Well
    0.82
     not
    0.73
     mắn
    0.73
     WELL
    0.72
     want
    0.71
    Activations Density 0.145%

    No Known Activations