© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 99424
    Prev
    Next
    INDEX
    Explanations

    references to methodological discussions and calculations in scientific studies

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

    results from tests

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     للمعارف
    -1.05
    featureID
    -0.93
    URLException
    -0.88
    GEBURTSDATUM
    -0.84
    contentLoaded
    -0.82
    tagHelperRunner
    -0.81
    OGND
    -0.80
    ंदीखरीदारी
    -0.80
    rungsseite
    -0.79
     AssemblyTitle
    -0.78
    POSITIVE LOGITS
     variations
    0.28
     aber
    0.26
     bisous
    0.26
     sujetos
    0.26
     personal
    0.25
     Fotograf
    0.25
     victims
    0.25
     however
    0.24
    ObjectModel
    0.24
    AndFlush
    0.24
    Activations Density 0.344%

    No Known Activations