© 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. 20-GEMMASCOPE-RES-131K
    11. 55307
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    tagHelperRunner
    -1.38
    complexType
    -1.09
    wts
    -0.84
     EconPapers
    -0.79
     أعلام
    -0.76
     disambiguazione
    -0.74
     toJson
    -0.70
     Waray
    -0.64
     ThemeData
    -0.60
    WriteBarrier
    -0.58
    POSITIVE LOGITS
    ServletRequest
    1.92
    ValueGenerated
    1.67
    orianCalendar
    0.91
    openSession
    0.44
    flashdata
    0.41
     voluntarily
    0.40
     Dundee
    0.39
     Journalism
    0.39
     voluntary
    0.39
     Rune
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.