© 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. 14748
    Prev
    Next
    INDEX
    Explanations

    proper nouns and significant identifiers in legal contexts

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

    Citations and references

    np_acts-logits-general · gemini-2.0-flash

    acronyms T

    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
    SequentialGroup
    -0.67
     Pierson
    -0.46
    ässä
    -0.45
    鹅
    -0.43
     Reese
    -0.43
     conseillers
    -0.42
     Clarion
    -0.42
    iedenen
    -0.42
     Sequoia
    -0.41
     Clow
    -0.41
    POSITIVE LOGITS
     QT
    0.88
     JT
    0.87
     MT
    0.86
     NPT
    0.86
     CDT
    0.85
     CMT
    0.85
     CRT
    0.84
    QT
    0.84
    wt
    0.83
    Qt
    0.83
    Activations Density 2.501%

    No Known Activations