© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 60183
    Prev
    Next
    INDEX
    Explanations

    abbreviations or short forms related to biomedical or scientific terms

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

    ZEB, ZEB1, 0xeb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ligiloj
    -0.56
    richting
    -0.54
    perspective
    -0.52
    vierno
    -0.49
    yorsunuz
    -0.49
    ">>
    -0.48
    leistung
    -0.47
    Sito
    -0.47
    accompag
    -0.47
    তথ্যসূত্র
    -0.47
    POSITIVE LOGITS
    b
    0.84
    B
    0.76
     b
    0.72
    sb
    0.71
    ib
    0.71
     getB
    0.70
     CB
    0.68
    IB
    0.66
    cb
    0.65
     ib
    0.65
    Activations Density 0.301%

    No Known Activations