© 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. 8595
    Prev
    Next
    INDEX
    Explanations

    sequences of punctuation and numeric data in the text

    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
    SourceChecksum
    -1.25
    Personendaten
    -0.93
     ModelExpression
    -0.88
    webElementXpaths
    -0.85
     nahilalakip
    -0.82
     AspNetCore
    -0.82
     kasarigan
    -0.81
    ➯
    -0.81
    yntaxException
    -0.80
    IUrlHelper
    -0.80
    POSITIVE LOGITS
     
    0.66
    0
    0.40
    {
    0.39
     and
    0.35
    <eos>
    0.32
     gwaran
    0.32
     żad
    0.31
    <h2>
    0.30
     istnie
    0.30
     Instead
    0.29
    Activations Density 0.117%

    No Known Activations