© 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 EvalsExportsinterp-engineNEWAPI 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. 110852
    Prev
    Next
    INDEX
    Explanations

    specific legal terms and key figures associated with trials and legal situations

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

    Jordan insists, Murray Trial, Parliament building, pedestal sink

    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
    Citiți
    -0.47
    เท่า
    -0.42
     gemeinsamen
    -0.41
     colaboración
    -0.39
     Zusammenarbeit
    -0.39
     muun
    -0.39
     Técnica
    -0.38
     gemeinsame
    -0.38
     consecuencia
    -0.38
     Kerja
    -0.38
    POSITIVE LOGITS
    تقاوى
    0.99
     ویکی‌پدی
    0.94
    expandindo
    0.90
     Roskov
    0.90
     '\\;'
    0.85
    цездатний
    0.79
     himo
    0.79
    abestanden
    0.75
    Abitanti
    0.74
    IndentedString
    0.73
    Activations Density 0.254%

    No Known Activations