© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30391
    Prev
    Next
    INDEX
    Explanations

    attributes related to height in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.57
    bukkit
    -0.56
    createStatement
    -0.55
     faveur
    -0.53
     Pera
    -0.53
    GOTREF
    -0.49
     Polskiego
    -0.49
     AspNetCore
    -0.49
    ulkner
    -0.49
     composta
    -0.48
    POSITIVE LOGITS
    Portale
    0.81
     EnglishChoose
    0.70
    PyTuple
    0.69
     AssemblyVersion
    0.68
    ampingi
    0.65
    Datuak
    0.63
    øren
    0.60
    بوابة
    0.60
    EObject
    0.60
     chande
    0.59
    Activations Density 0.003%

    No Known Activations