© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 11524
    Prev
    Next
    INDEX
    Explanations

    numeric data types and operations related to them

    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
     الحره
    -0.69
    lső
    -0.68
    日発売
    -0.64
     respectivos
    -0.63
     ujednoznacz
    -0.63
     múltiples
    -0.62
     vidare
    -0.62
    IUrlHelper
    -0.61
    itoire
    -0.61
    ViewImports
    -0.60
    POSITIVE LOGITS
     AtomicInteger
    0.76
    IntegerField
    0.76
     AssemblyVersion
    0.67
    GetAxis
    0.65
    FloatField
    0.64
    DecimalFormat
    0.61
     math
    0.60
    strconv
    0.59
    ometers
    0.56
     arithmetic
    0.56
    Activations Density 0.425%

    No Known Activations