© 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. 3-GEMMASCOPE-RES-16K
    11. 10891
    Prev
    Next
    INDEX
    Explanations

    data type declarations and associated functionalities in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.98
    bootstrapcdn
    -0.73
     AssemblyCompany
    -0.72
    tagHelperRunner
    -0.64
    
    -0.63
    Hochspringen
    -0.61
    CppMethod
    -0.61
     estekak
    -0.60
     Taktlose
    -0.60
     незавершена
    -0.58
    POSITIVE LOGITS
    Float
    1.59
    Double
    1.47
     Float
    1.44
     Double
    1.38
     Long
    1.31
    Long
    1.27
    Integer
    1.16
     Integer
    1.15
    Boolean
    0.98
     Boolean
    0.93
    Activations Density 0.163%

    No Known Activations