© 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. 9601
    Prev
    Next
    INDEX
    Explanations

    references to corruption and real estate scandals involving government officials

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

    Chinese provinces or regions

    np_acts-logits-general · gemini-2.0-flash

    Shandong provinces housing

    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
    ®:
    -0.80
    ®,
    -0.67
    ®
    -0.66
    ®.
    -0.65
     (&
    -0.63
     ™
    -0.58
     Proprietary
    -0.57
    actéristique
    -0.56
     ();
    -0.56
    *;
    -0.56
    POSITIVE LOGITS
     zufolge
    0.66
     demnach
    0.61
     vorigen
    0.60
    -
    0.60
    請繼續往下閱讀
    0.59
     amid
    0.57
     bourse
    0.56
     विश्वसनीयता
    0.54
     saurait
    0.54
    ardoor
    0.54
    Activations Density 0.069%

    No Known Activations