© 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. 3342
    Prev
    Next
    INDEX
    Explanations

    connections and interactions within mechanical and engineering contexts

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

    Prepositions followed by articles or adjectives

    np_acts-logits-general · gemini-2.0-flash

    prepositions followed by articles

    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
    OGND
    -1.17
    IsMutable
    -1.02
    webElementXpaths
    -0.98
     للاسماء
    -0.93
     Italijanski
    -0.90
     مرئيه
    -0.90
    featureID
    -0.90
    Autoritní
    -0.89
     disambiguazione
    -0.88
    IndentedString
    -0.88
    POSITIVE LOGITS
     a
    0.59
     an
    0.45
     sebuah
    0.39
     suatu
    0.36
     large
    0.35
     three
    0.34
     simple
    0.34
     numerous
    0.34
     six
    0.33
     five
    0.33
    Activations Density 1.022%

    No Known Activations