© 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. 8052
    Prev
    Next
    INDEX
    Explanations

    XML or HTML tag structures and elements

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

    XML or similar tag delimiters

    np_acts-logits-general · gemini-2.0-flash

    markup and code structures

    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
    Jeografia
    -0.63
    parsedMessage
    -0.63
    RegressionTest
    -0.59
     &___
    -0.58
     ligiloj
    -0.57
    AISSEE
    -0.57
    adaptiveStyles
    -0.54
    nezeu
    -0.52
    <%=
    -0.50
     Autorisations
    -0.50
    POSITIVE LOGITS
    Diweddarwch
    0.50
     صوتيه
    0.40
     nahilalakip
    0.40
    Tembelea
    0.39
     leão
    0.39
    URLException
    0.35
    MemoryWarning
    0.34
     nuits
    0.34
     brinquedo
    0.33
    BeginInit
    0.32
    Activations Density 0.260%

    No Known Activations