© 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. 20-GEMMASCOPE-RES-16K
    11. 5835
    Prev
    Next
    INDEX
    Explanations

    references to academic programs and their rankings

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

    Rankings, especially "Fast 50," "40 under 40", or Michelin-starred restaurants

    np_acts-logits-general · gemini-2.0-flash

    ranking or rated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -0.84
    .*")]
    -0.77
    aarrggbb
    -0.74
     NSCoder
    -0.70
    audiovisuel
    -0.70
    rungsseite
    -0.68
    prüche
    -0.67
    Gambas
    -0.67
     tartalomajánló
    -0.67
    featureID
    -0.66
    POSITIVE LOGITS
     ranked
    1.10
     ranking
    1.09
     rankings
    1.07
     Ranked
    0.91
     rated
    0.87
     Ranking
    0.87
    ranked
    0.87
     recognition
    0.83
    ranking
    0.83
    Ranked
    0.81
    Activations Density 0.148%

    No Known Activations