© 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. 1-GEMMASCOPE-RES-16K
    6. 6339
    Prev
    Next
    INDEX
    Explanations

    the name "Andrew"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <!--[
    -0.60
     समीक्षाओं
    -0.59
     مشين
    -0.58
     honor
    -0.58
     ICollection
    -0.58
     ItemStack
    -0.56
     ratios
    -0.56
    matchCondition
    -0.55
    Buster
    -0.55
     considérons
    -0.54
    POSITIVE LOGITS
     refresh
    0.72
    refresh
    0.71
     Refresh
    0.71
     AssemblyTitle
    0.66
    Refresh
    0.63
     deposition
    0.62
     pseudo
    0.61
     Andrew
    0.60
     rafraî
    0.58
    REFRESH
    0.57
    Activations Density 0.047%

    No Known Activations