© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9536
    Prev
    Next
    INDEX
    Explanations

    family relationships and connections in obituaries

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

    Tokens preceding specific prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    exchanges, slots, means

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.47
    См
    -0.39
    IUrlHelper
    -0.38
    GTC
    -0.36
    Merge
    -0.34
    sidenav
    -0.33
    smooth
    -0.33
     Lokales
    -0.33
     invokingState
    -0.32
    Intervention
    -0.32
    POSITIVE LOGITS
    RegressionTest
    0.80
    WebElementEntity
    0.66
     AssemblyTitle
    0.63
    
    0.58
     שוליים
    0.54
    inSlope
    0.52
    ]%
    0.47
    تقاوى
    0.45
    SharedDtor
    0.45
     intStringLen
    0.45
    Activations Density 0.042%

    No Known Activations