© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 33-GEMMASCOPE-RES-16K
    11. 1423
    Prev
    Next
    INDEX
    Explanations

    mathematical notation related to set theory and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posedge
    -0.46
     reser
    -0.42
     Autorizaciones
    -0.42
    揄
    -0.41
    errHandler
    -0.41
     ProtoMessage
    -0.40
    copg
    -0.40
    LayoutConstraint
    -0.39
     мәкал
    -0.39
    addContainerGap
    -0.38
    POSITIVE LOGITS
     $\{
    1.29
     \{
    1.20
     {
    1.17
    \{
    1.14
     $\{\
    1.05
     $\{$
    1.04
    $\{
    1.02
    ｛
    1.02
    {
    0.93
    {
    0.90
    Activations Density 1.716%

    No Known Activations