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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14559
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistical measurements related to scientific research

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

    medical, scientific, and technical terms

    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
     nahilalakip
    -0.60
    Tembelea
    -0.60
    expandindo
    -0.58
    ьажоргаш
    -0.58
     насељу
    -0.57
     Chwiliwch
    -0.54
    QMetaType
    -0.54
    setViewportView
    -0.54
    rungsseite
    -0.50
     treasury
    -0.50
    POSITIVE LOGITS
    TargetException
    0.45
    AlterField
    0.44
    évaluateur
    0.43
    ExtendWith
    0.42
    ValueGeneration
    0.40
    RegressionTest
    0.40
     Biôgrafia
    0.40
     espoir
    0.39
    fortawesome
    0.39
    raszamy
    0.38
    Activations Density 0.253%

    No Known Activations