© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7269
    Prev
    Next
    INDEX
    Explanations

    frequent use of the word "just" and its variants in various contexts

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

    Adverbs/qualifiers before adjectives

    np_acts-logits-general · gemini-2.0-flash

    intensifiers and qualifiers

    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
     autorytatywna
    -0.35
    ⓧ
    -0.28
     wands
    -0.27
     priests
    -0.27
    
    -0.26
    ActionButton
    -0.26
     pará
    -0.26
    JvmStatic
    -0.26
     primas
    -0.26
    Ident
    -0.25
    POSITIVE LOGITS
     AssemblyTitle
    0.65
     jScrollPane
    0.63
    MENAFN
    0.60
     dAtA
    0.59
     للمعارف
    0.59
    AddTagHelper
    0.58
    XmlRootElement
    0.58
     otomatig
    0.55
    ksikon
    0.54
     مشين
    0.53
    Activations Density 0.546%

    No Known Activations