© 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. 24-GEMMASCOPE-RES-16K
    6. 12010
    Prev
    Next
    INDEX
    Explanations

    the presence of the article "an" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "an" followed by adjective

    np_acts-logits-general · gemini-2.0-flash

    an followed by a descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.82
    GEBURTSDATUM
    -0.80
    WriteTagHelper
    -0.79
    OGND
    -0.78
     незавершена
    -0.74
    complexContent
    -0.73
     مشين
    -0.72
    setVerticalGroup
    -0.72
     ligiloj
    -0.71
    assemblée
    -0.71
    POSITIVE LOGITS
     assortment
    0.63
     array
    0.63
     entire
    0.59
     alternative
    0.57
     important
    0.56
     amazing
    0.55
     active
    0.55
     excellent
    0.55
     example
    0.55
     abundance
    0.54
    Activations Density 0.352%

    No Known Activations