© 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. 14-GEMMASCOPE-RES-16K
    6. 12365
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and expressions of doubt or inquiry

    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
    addGap
    -0.55
    Aholisi
    -0.53
    addPreferredGap
    -0.52
    XMLSchema
    -0.50
     anis
    -0.48
    avajillas
    -0.48
     GetEnumerator
    -0.48
     folio
    -0.47
     AssemblyCompany
    -0.47
    CodeAttribute
    -0.47
    POSITIVE LOGITS
     ujednoznacz
    0.73
     nantinya
    0.67
    万一
    0.66
     mocht
    0.57
     curious
    0.56
     besoin
    0.56
     Bedarf
    0.56
    řeba
    0.55
     Int
    0.55
     évent
    0.55
    Activations Density 0.199%

    No Known Activations