© 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. 3-GEMMASCOPE-RES-16K
    11. 8509
    Prev
    Next
    INDEX
    Explanations

    elements related to error messages and programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]);
    -0.59
    ")){
    -0.58
    "){
    -0.57
    '])
    -0.57
    _
    -0.56
    "]=
    -0.56
    ']);
    -0.55
    '){
    -0.55
    "))
    -0.55
    "])
    -0.54
    POSITIVE LOGITS
    ſelves
    0.75
     queſta
    0.70
    ſelf
    0.70
    ForRow
    0.67
     ſche
    0.66
    ToScroll
    0.65
     ErrInvalid
    0.65
     AssemblyVersion
    0.64
     ſta
    0.63
     stockbild
    0.63
    Activations Density 0.509%

    No Known Activations