© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 21443
    Prev
    Next
    INDEX
    Explanations

    mentions of constructors and initialization methods in programming code

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

    constructor and initialization

    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
    iParam
    -0.42
     also
    -0.37
     eventual
    -0.36
    Читати
    -0.33
     eingel
    -0.32
     MainAxisSize
    -0.32
     también
    -0.32
     tah
    -0.31
     associated
    -0.30
    xrLabel
    -0.30
    POSITIVE LOGITS
     initComponents
    1.02
    constructor
    0.93
     autorytatywna
    0.80
    WriteTagHelper
    0.73
    ArgsConstructor
    0.66
    XmlAccessorType
    0.60
     للمعارف
    0.58
    SharedDtor
    0.56
    MemoryWarning
    0.56
    construct
    0.54
    Activations Density 0.001%

    No Known Activations