© 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. 0-GEMMASCOPE-RES-16K
    11. 8304
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and named entities related to assembly and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.41
    GEBURTSDATUM
    -0.40
     Gebir
    -0.39
    ężczy
    -0.38
     pymysql
    -0.38
    FieldOffset
    -0.36
    lorette
    -0.36
    amsmath
    -0.35
     cuánto
    -0.35
     restaurar
    -0.35
    POSITIVE LOGITS
     AssemblyCulture
    0.57
    MK
    0.52
     cou
    0.52
     wildcard
    0.52
     Brand
    0.51
    addCriterion
    0.51
     serviced
    0.50
     wild
    0.50
     Brands
    0.49
     regulated
    0.49
    Activations Density 1.711%

    No Known Activations