© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28494
    Prev
    Next
    INDEX
    Explanations

    terms related to financial projections and general economic conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sequential conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initially
    -0.41
    owieck
    -0.41
     relates
    -0.39
    ]]]
    -0.39
    WEBPACK
    -0.39
    PerformLayout
    -0.39
     indirectly
    -0.38
    يا
    -0.38
     previa
    -0.38
    :"-"`
    -0.38
    POSITIVE LOGITS
     then
    1.80
    then
    1.59
     Then
    1.41
    Then
    1.39
     Daarna
    1.38
     THEN
    1.34
     thereafter
    1.33
     Danach
    1.30
     Thereafter
    1.30
    THEN
    1.27
    Activations Density 0.263%

    No Known Activations