© 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. 13250
    Prev
    Next
    INDEX
    Explanations

    terms related to "double" or "dual" concepts

    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
    Datuak
    -0.65
     newBuilder
    -0.62
     selanjutnya
    -0.61
     vettoriale
    -0.61
     dépos
    -0.58
    Virgo
    -0.58
     EoL
    -0.58
     oreille
    -0.57
    tschaft
    -0.57
    cmap
    -0.56
    POSITIVE LOGITS
     double
    3.54
    double
    3.24
     Double
    3.23
     DOUBLE
    3.15
    Double
    3.14
    DOUBLE
    2.89
     doubles
    2.83
     doble
    2.56
    doubles
    2.51
     Doubles
    2.49
    Activations Density 0.086%

    No Known Activations