© 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. 28-GEMMASCOPE-RES-16K
    11. 7828
    Prev
    Next
    INDEX
    Explanations

    specific phrases or terms associated with data structures and performance metrics

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

    Iterating through stages or steps

    np_acts-logits-general · gemini-2.0-flash

    following "each"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.89
    parsedMessage
    -0.61
     للمعارف
    -0.60
     שוליים
    -0.59
    VYMaps
    -0.59
    ientras
    -0.58
     snippetHide
    -0.57
     EconPapers
    -0.56
     AssemblyCompany
    -0.56
    참고
    -0.56
    POSITIVE LOGITS
     sections
    0.82
     section
    0.71
     stages
    0.59
     secciones
    0.55
     chapters
    0.53
     Sections
    0.53
     elements
    0.52
     nodes
    0.52
     stage
    0.52
     modules
    0.52
    Activations Density 1.222%

    No Known Activations