© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8054
    Prev
    Next
    INDEX
    Explanations

    elements related to the structure and formatting of documents, such as figures, sections, and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sure
    -0.37
     HON
    -0.30
     shrink
    -0.30
    良
    -0.30
     разо
    -0.30
     
    -0.28
    Sure
    -0.28
     sund
    -0.28
    <eos>
    -0.27
     tro
    -0.27
    POSITIVE LOGITS
    sizeCache
    0.98
    Vidite
    0.82
    SourceChecksum
    0.79
    expandindo
    0.78
    parsedMessage
    0.73
     resourceCulture
    0.67
     AssemblyCompany
    0.66
    principalColumn
    0.65
    GOTREF
    0.64
    verwijspagina
    0.64
    Activations Density 0.291%

    No Known Activations