© 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. 31-GEMMASCOPE-RES-16K
    11. 13087
    Prev
    Next
    INDEX
    Explanations

    key financial terms related to mergers and acquisitions

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

    business transactions involving mergers, acquisitions, and financial deals.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trá
    -0.28
     yerde
    -0.28
     цве
    -0.28
     pengh
    -0.27
     écou
    -0.26
    inscrire
    -0.26
     yoktur
    -0.26
    Booking
    -0.26
    :+:
    -0.25
     test
    -0.25
    POSITIVE LOGITS
     acquisition
    1.45
     Acquisition
    1.26
     acquisitions
    1.26
    acquisition
    1.26
     acquired
    1.25
    Acquisition
    1.25
     acquiring
    1.19
     acquire
    1.17
     takeover
    1.17
    acquired
    1.16
    Activations Density 0.341%

    No Known Activations