© 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. 27217
    Prev
    Next
    INDEX
    Explanations

    locations and names associated with events or institutions

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

    specific places, events, or institutions

    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
     calendriers
    -0.45
     tesettür
    -0.42
     femininos
    -0.42
     kumaş
    -0.40
     nė
    -0.37
     världen
    -0.37
     geleverd
    -0.37
     gevolg
    -0.36
     suaminya
    -0.36
     boneka
    -0.35
    POSITIVE LOGITS
     dort
    0.69
     allí
    0.63
     там
    0.63
     therein
    0.58
     ब्रेकडाउन
    0.55
     שם
    0.54
    在那里
    0.54
    adpleegd
    0.53
     &___
    0.52
     مرئيه
    0.52
    Activations Density 0.106%

    No Known Activations