© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 111295
    Prev
    Next
    INDEX
    Explanations

    concepts related to the challenges and complexities of personal beliefs and experiences

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

    spending money

    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
    Zusammen
    -0.34
    vad
    -0.32
    grim
    -0.32
    合って
    -0.31
    fail
    -0.30
     bram
    -0.30
    الحياه
    -0.29
     hadas
    -0.29
    together
    -0.29
    卢
    -0.29
    POSITIVE LOGITS
     يتيمه
    0.72
    parsedMessage
    0.70
     kaarangay
    0.66
     <<<<<<<<<<<<<<
    0.65
     Lightboxes
    0.58
    ſelves
    0.57
    featureID
    0.56
    存于互联网档案馆
    0.55
     själva
    0.55
    oa̍t
    0.54
    Activations Density 0.066%

    No Known Activations