© 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. 14578
    Prev
    Next
    INDEX
    Explanations

    references to scientific classifications and authors related to the study of species

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

    Regan Zimin Engl

    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
     للاسماء
    -0.91
     ujednoznacz
    -0.66
     NSCoder
    -0.65
     EconPapers
    -0.57
    yarnpkg
    -0.57
     محفوظة
    -0.56
    Vanjske
    -0.56
    principalColumn
    -0.56
    RegressionTest
    -0.55
    Personensuche
    -0.54
    POSITIVE LOGITS
     Winaray
    0.39
    cemment
    0.32
     recognized
    0.32
    berdayakan
    0.31
    zył
    0.30
     nouvel
    0.29
     Tan
    0.29
     década
    0.29
     soins
    0.28
    stunde
    0.28
    Activations Density 0.016%

    No Known Activations