© 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. 8569
    Prev
    Next
    INDEX
    Explanations

    quotations and references to specific structured data or code elements

    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
     desmotivaciones
    -1.59
     queſta
    -1.49
     Paglinawan
    -1.45
     miniaturka
    -1.44
     increí
    -1.44
     indígen
    -1.41
     autorytatywna
    -1.41
     Comprometido
    -1.32
    berdayakan
    -1.31
     ainfi
    -1.30
    POSITIVE LOGITS
    .
    1.92
     
    1.59
    ,
    1.49
    -
    1.38
    _
    1.36
     (
    1.34
    ↵
    1.32
     to
    1.32
     in
    1.29
    1
    1.28
    Activations Density 2.933%

    No Known Activations