© 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. 27190
    Prev
    Next
    INDEX
    Explanations

    coding-related syntax or structure in programming

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

    non-English words

    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
    featureID
    -1.15
     Administrativna
    -1.03
     resourceCulture
    -0.95
    iſchen
    -0.94
     kasarigan
    -0.93
     Biôgrafia
    -0.90
     Italijanski
    -0.88
    oa̍t
    -0.88
     ligiloj
    -0.88
    AISSEE
    -0.87
    POSITIVE LOGITS
     burbujas
    0.35
     ayrıca
    0.31
     secundario
    0.28
     nuages
    0.27
    reszcie
    0.27
     courants
    0.27
    1
    0.27
     palacio
    0.26
     agujas
    0.25
     velas
    0.25
    Activations Density 0.001%

    No Known Activations