© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 5459
    Prev
    Next
    INDEX
    Explanations

    elements of code related to data structure definitions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.45
    toFloat
    -0.39
    setString
    -0.38
    toDouble
    -0.38
     obje
    -0.38
     atof
    -0.38
    Urls
    -0.37
     ModelAndView
    -0.37
     Belle
    -0.37
     vena
    -0.37
    POSITIVE LOGITS
     ब्रेकडाउन
    0.62
     uint
    0.56
     disambiguazione
    0.55
     u
    0.54
     firmar
    0.50
    Aktualisiert
    0.50
    uint
    0.50
     signed
    0.50
    signed
    0.49
    SourceChecksum
    0.48
    Activations Density 0.736%

    No Known Activations