© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 8408
    Prev
    Next
    INDEX
    Explanations

    sentences that begin with a specific structured phrase or element in a text, indicating the start of a new section or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.95
    цездатний
    -0.92
    Архівовано
    -0.86
    webElementXpaths
    -0.84
    ագրություններ
    -0.84
    ArrowToggle
    -0.82
    InjectAttribute
    -0.81
    Искәрмәләр
    -0.79
     unknownFields
    -0.78
     مرئيه
    -0.78
    POSITIVE LOGITS
    IsContent
    3.66
     Kind
    0.50
     olisi
    0.46
    <bos>
    0.45
     kind
    0.45
     trataba
    0.45
     maternelle
    0.44
    resultados
    0.41
    CreateModel
    0.40
     listos
    0.40
    Activations Density 0.005%

    No Known Activations