© 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. 3706
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate statistical averages or trends

    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
     ainfi
    -1.30
     indígen
    -1.27
     mauva
    -1.20
     miniaturka
    -1.20
     plufieurs
    -1.17
     auroit
    -1.15
     Monfieur
    -1.15
    genodigd
    -1.15
    <unused41>
    -1.11
    <unused42>
    -1.11
    POSITIVE LOGITS
     in
    1.77
     for
    0.94
    ,
    0.92
     
    0.89
     of
    0.89
     as
    0.87
     on
    0.79
     to
    0.79
     at
    0.79
     a
    0.75
    Activations Density 1.130%

    No Known Activations