Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 16071
    Prev
    Next
    INDEX
    Explanations

    concepts related to practicality and real-world application

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    InputBorder
    -0.93
    quelize
    -0.93
    ResponseWriter
    -0.90
    numerusform
    -0.87
    oneofs
    -0.86
     noDo
    -0.83
    usermodel
    -0.81
    Controllo
    -0.77
     disambiguazione
    -0.75
     defaultstate
    -0.75
    POSITIVE LOGITS
     practical
    2.73
     Practical
    2.55
    Practical
    2.54
    practical
    2.48
     PRACTICAL
    2.26
     práctico
    1.89
     praktische
    1.78
     practicality
    1.76
     prácti
    1.72
     prak
    1.69
    Activations Density 0.065%

    No Known Activations