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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13-GEMMASCOPE-RES-16K
    6. 11212
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to grading and scoring systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.72
     AssemblyProduct
    -0.63
    FormTagHelper
    -0.63
    ChildIndex
    -0.56
     Hood
    -0.52
    awtextra
    -0.51
    makeConstraints
    -0.51
    RoutingModule
    -0.50
     שוליים
    -0.50
    jsxFileName
    -0.50
    POSITIVE LOGITS
     MutableLiveData
    0.59
     kasarigan
    0.54
    NewValue
    0.52
    orianCalendar
    0.50
    bán
    0.48
     Janis
    0.47
    ">:
    0.47
    annya
    0.47
     ?>>
    0.47
    Value
    0.47
    Activations Density 1.082%

    No Known Activations